Merge branch 'feature/linenoise-ng' of git://github.com/dtzWill/nix
This commit is contained in:
commit
5ba5ca7888
|
@ -262,7 +262,7 @@ xlink:href="http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html">GNU
|
|||
LGPLv2.1 or (at your option) any later version</link>.</para>
|
||||
|
||||
<para>Nix uses the <link
|
||||
xlink:href="https://github.com/antirez/linenoise">linenoise
|
||||
xlink:href="https://github.com/arangodb/linenoise-ng">linenoise-ng
|
||||
library</link>, which has the following license:</para>
|
||||
|
||||
<programlisting><xi:include href="../../../src/linenoise/LICENSE" parse="text" /></programlisting>
|
||||
|
|
542
src/linenoise/ConvertUTF.cpp
Normal file
542
src/linenoise/ConvertUTF.cpp
Normal file
|
@ -0,0 +1,542 @@
|
|||
/*
|
||||
* Copyright 2001-2004 Unicode, Inc.
|
||||
*
|
||||
* Disclaimer
|
||||
*
|
||||
* This source code is provided as is by Unicode, Inc. No claims are
|
||||
* made as to fitness for any particular purpose. No warranties of any
|
||||
* kind are expressed or implied. The recipient agrees to determine
|
||||
* applicability of information provided. If this file has been
|
||||
* purchased on magnetic or optical media from Unicode, Inc., the
|
||||
* sole remedy for any claim will be exchange of defective media
|
||||
* within 90 days of receipt.
|
||||
*
|
||||
* Limitations on Rights to Redistribute This Code
|
||||
*
|
||||
* Unicode, Inc. hereby grants the right to freely use the information
|
||||
* supplied in this file in the creation of products supporting the
|
||||
* Unicode Standard, and to make copies of this file in any form
|
||||
* for internal or external distribution as long as this notice
|
||||
* remains attached.
|
||||
*/
|
||||
|
||||
/* ---------------------------------------------------------------------
|
||||
|
||||
Conversions between UTF32, UTF-16, and UTF-8. Source code file.
|
||||
Author: Mark E. Davis, 1994.
|
||||
Rev History: Rick McGowan, fixes & updates May 2001.
|
||||
Sept 2001: fixed const & error conditions per
|
||||
mods suggested by S. Parent & A. Lillich.
|
||||
June 2002: Tim Dodd added detection and handling of incomplete
|
||||
source sequences, enhanced error detection, added casts
|
||||
to eliminate compiler warnings.
|
||||
July 2003: slight mods to back out aggressive FFFE detection.
|
||||
Jan 2004: updated switches in from-UTF8 conversions.
|
||||
Oct 2004: updated to use UNI_MAX_LEGAL_UTF32 in UTF-32 conversions.
|
||||
|
||||
See the header file "ConvertUTF.h" for complete documentation.
|
||||
|
||||
------------------------------------------------------------------------ */
|
||||
|
||||
#include "ConvertUTF.h"
|
||||
#ifdef CVTUTF_DEBUG
|
||||
#include <stdio.h>
|
||||
#endif
|
||||
|
||||
namespace linenoise_ng {
|
||||
|
||||
static const int halfShift = 10; /* used for shifting by 10 bits */
|
||||
|
||||
static const UTF32 halfBase = 0x0010000UL;
|
||||
static const UTF32 halfMask = 0x3FFUL;
|
||||
|
||||
#define UNI_SUR_HIGH_START (UTF32)0xD800
|
||||
#define UNI_SUR_HIGH_END (UTF32)0xDBFF
|
||||
#define UNI_SUR_LOW_START (UTF32)0xDC00
|
||||
#define UNI_SUR_LOW_END (UTF32)0xDFFF
|
||||
#define false 0
|
||||
#define true 1
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
ConversionResult ConvertUTF32toUTF16 (
|
||||
const UTF32** sourceStart, const UTF32* sourceEnd,
|
||||
char16_t** targetStart, char16_t* targetEnd, ConversionFlags flags) {
|
||||
ConversionResult result = conversionOK;
|
||||
const UTF32* source = *sourceStart;
|
||||
char16_t* target = *targetStart;
|
||||
while (source < sourceEnd) {
|
||||
UTF32 ch;
|
||||
if (target >= targetEnd) {
|
||||
result = targetExhausted; break;
|
||||
}
|
||||
ch = *source++;
|
||||
if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */
|
||||
/* UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values */
|
||||
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
|
||||
if (flags == strictConversion) {
|
||||
--source; /* return to the illegal value itself */
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
} else {
|
||||
*target++ = UNI_REPLACEMENT_CHAR;
|
||||
}
|
||||
} else {
|
||||
*target++ = (UTF16)ch; /* normal case */
|
||||
}
|
||||
} else if (ch > UNI_MAX_LEGAL_UTF32) {
|
||||
if (flags == strictConversion) {
|
||||
result = sourceIllegal;
|
||||
} else {
|
||||
*target++ = UNI_REPLACEMENT_CHAR;
|
||||
}
|
||||
} else {
|
||||
/* target is a character in range 0xFFFF - 0x10FFFF. */
|
||||
if (target + 1 >= targetEnd) {
|
||||
--source; /* Back up source pointer! */
|
||||
result = targetExhausted; break;
|
||||
}
|
||||
ch -= halfBase;
|
||||
*target++ = (UTF16)((ch >> halfShift) + UNI_SUR_HIGH_START);
|
||||
*target++ = (UTF16)((ch & halfMask) + UNI_SUR_LOW_START);
|
||||
}
|
||||
}
|
||||
*sourceStart = source;
|
||||
*targetStart = target;
|
||||
return result;
|
||||
}
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
ConversionResult ConvertUTF16toUTF32 (
|
||||
const UTF16** sourceStart, const UTF16* sourceEnd,
|
||||
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
|
||||
ConversionResult result = conversionOK;
|
||||
const UTF16* source = *sourceStart;
|
||||
UTF32* target = *targetStart;
|
||||
UTF32 ch, ch2;
|
||||
while (source < sourceEnd) {
|
||||
const UTF16* oldSource = source; /* In case we have to back up because of target overflow. */
|
||||
ch = *source++;
|
||||
/* If we have a surrogate pair, convert to UTF32 first. */
|
||||
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END) {
|
||||
/* If the 16 bits following the high surrogate are in the source buffer... */
|
||||
if (source < sourceEnd) {
|
||||
ch2 = *source;
|
||||
/* If it's a low surrogate, convert to UTF32. */
|
||||
if (ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END) {
|
||||
ch = ((ch - UNI_SUR_HIGH_START) << halfShift)
|
||||
+ (ch2 - UNI_SUR_LOW_START) + halfBase;
|
||||
++source;
|
||||
} else if (flags == strictConversion) { /* it's an unpaired high surrogate */
|
||||
--source; /* return to the illegal value itself */
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
}
|
||||
} else { /* We don't have the 16 bits following the high surrogate. */
|
||||
--source; /* return to the high surrogate */
|
||||
result = sourceExhausted;
|
||||
break;
|
||||
}
|
||||
} else if (flags == strictConversion) {
|
||||
/* UTF-16 surrogate values are illegal in UTF-32 */
|
||||
if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
|
||||
--source; /* return to the illegal value itself */
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (target >= targetEnd) {
|
||||
source = oldSource; /* Back up source pointer! */
|
||||
result = targetExhausted; break;
|
||||
}
|
||||
*target++ = ch;
|
||||
}
|
||||
*sourceStart = source;
|
||||
*targetStart = target;
|
||||
#ifdef CVTUTF_DEBUG
|
||||
if (result == sourceIllegal) {
|
||||
fprintf(stderr, "ConvertUTF16toUTF32 illegal seq 0x%04x,%04x\n", ch, ch2);
|
||||
fflush(stderr);
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
/*
|
||||
* Index into the table below with the first byte of a UTF-8 sequence to
|
||||
* get the number of trailing bytes that are supposed to follow it.
|
||||
* Note that *legal* UTF-8 values can't have 4 or 5-bytes. The table is
|
||||
* left as-is for anyone who may want to do such conversion, which was
|
||||
* allowed in earlier algorithms.
|
||||
*/
|
||||
static const char trailingBytesForUTF8[256] = {
|
||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
||||
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
||||
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
|
||||
};
|
||||
|
||||
/*
|
||||
* Magic values subtracted from a buffer value during UTF8 conversion.
|
||||
* This table contains as many values as there might be trailing bytes
|
||||
* in a UTF-8 sequence.
|
||||
*/
|
||||
static const UTF32 offsetsFromUTF8[6] = { 0x00000000UL, 0x00003080UL, 0x000E2080UL,
|
||||
0x03C82080UL, 0xFA082080UL, 0x82082080UL };
|
||||
|
||||
/*
|
||||
* Once the bits are split out into bytes of UTF-8, this is a mask OR-ed
|
||||
* into the first byte, depending on how many bytes follow. There are
|
||||
* as many entries in this table as there are UTF-8 sequence types.
|
||||
* (I.e., one byte sequence, two byte... etc.). Remember that sequencs
|
||||
* for *legal* UTF-8 will be 4 or fewer bytes total.
|
||||
*/
|
||||
static const UTF8 firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
/* The interface converts a whole buffer to avoid function-call overhead.
|
||||
* Constants have been gathered. Loops & conditionals have been removed as
|
||||
* much as possible for efficiency, in favor of drop-through switches.
|
||||
* (See "Note A" at the bottom of the file for equivalent code.)
|
||||
* If your compiler supports it, the "isLegalUTF8" call can be turned
|
||||
* into an inline function.
|
||||
*/
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
ConversionResult ConvertUTF16toUTF8 (
|
||||
const UTF16** sourceStart, const UTF16* sourceEnd,
|
||||
UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
|
||||
ConversionResult result = conversionOK;
|
||||
const UTF16* source = *sourceStart;
|
||||
UTF8* target = *targetStart;
|
||||
while (source < sourceEnd) {
|
||||
UTF32 ch;
|
||||
unsigned short bytesToWrite = 0;
|
||||
const UTF32 byteMask = 0xBF;
|
||||
const UTF32 byteMark = 0x80;
|
||||
const UTF16* oldSource = source; /* In case we have to back up because of target overflow. */
|
||||
ch = *source++;
|
||||
/* If we have a surrogate pair, convert to UTF32 first. */
|
||||
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END) {
|
||||
/* If the 16 bits following the high surrogate are in the source buffer... */
|
||||
if (source < sourceEnd) {
|
||||
UTF32 ch2 = *source;
|
||||
/* If it's a low surrogate, convert to UTF32. */
|
||||
if (ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END) {
|
||||
ch = ((ch - UNI_SUR_HIGH_START) << halfShift)
|
||||
+ (ch2 - UNI_SUR_LOW_START) + halfBase;
|
||||
++source;
|
||||
} else if (flags == strictConversion) { /* it's an unpaired high surrogate */
|
||||
--source; /* return to the illegal value itself */
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
}
|
||||
} else { /* We don't have the 16 bits following the high surrogate. */
|
||||
--source; /* return to the high surrogate */
|
||||
result = sourceExhausted;
|
||||
break;
|
||||
}
|
||||
} else if (flags == strictConversion) {
|
||||
/* UTF-16 surrogate values are illegal in UTF-32 */
|
||||
if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
|
||||
--source; /* return to the illegal value itself */
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
}
|
||||
}
|
||||
/* Figure out how many bytes the result will require */
|
||||
if (ch < (UTF32)0x80) { bytesToWrite = 1;
|
||||
} else if (ch < (UTF32)0x800) { bytesToWrite = 2;
|
||||
} else if (ch < (UTF32)0x10000) { bytesToWrite = 3;
|
||||
} else if (ch < (UTF32)0x110000) { bytesToWrite = 4;
|
||||
} else { bytesToWrite = 3;
|
||||
ch = UNI_REPLACEMENT_CHAR;
|
||||
}
|
||||
|
||||
target += bytesToWrite;
|
||||
if (target > targetEnd) {
|
||||
source = oldSource; /* Back up source pointer! */
|
||||
target -= bytesToWrite; result = targetExhausted; break;
|
||||
}
|
||||
switch (bytesToWrite) { /* note: everything falls through. */
|
||||
case 4: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
|
||||
case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
|
||||
case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
|
||||
case 1: *--target = (UTF8)(ch | firstByteMark[bytesToWrite]);
|
||||
}
|
||||
target += bytesToWrite;
|
||||
}
|
||||
*sourceStart = source;
|
||||
*targetStart = target;
|
||||
return result;
|
||||
}
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
/*
|
||||
* Utility routine to tell whether a sequence of bytes is legal UTF-8.
|
||||
* This must be called with the length pre-determined by the first byte.
|
||||
* If not calling this from ConvertUTF8to*, then the length can be set by:
|
||||
* length = trailingBytesForUTF8[*source]+1;
|
||||
* and the sequence is illegal right away if there aren't that many bytes
|
||||
* available.
|
||||
* If presented with a length > 4, this returns false. The Unicode
|
||||
* definition of UTF-8 goes up to 4-byte sequences.
|
||||
*/
|
||||
|
||||
static Boolean isLegalUTF8(const UTF8 *source, int length) {
|
||||
UTF8 a;
|
||||
const UTF8 *srcptr = source+length;
|
||||
switch (length) {
|
||||
default: return false;
|
||||
/* Everything else falls through when "true"... */
|
||||
case 4: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
|
||||
case 3: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
|
||||
case 2: if ((a = (*--srcptr)) > 0xBF) return false;
|
||||
|
||||
switch (*source) {
|
||||
/* no fall-through in this inner switch */
|
||||
case 0xE0: if (a < 0xA0) return false; break;
|
||||
case 0xED: if (a > 0x9F) return false; break;
|
||||
case 0xF0: if (a < 0x90) return false; break;
|
||||
case 0xF4: if (a > 0x8F) return false; break;
|
||||
default: if (a < 0x80) return false;
|
||||
}
|
||||
|
||||
case 1: if (*source >= 0x80 && *source < 0xC2) return false;
|
||||
}
|
||||
if (*source > 0xF4) return false;
|
||||
return true;
|
||||
}
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
/*
|
||||
* Exported function to return whether a UTF-8 sequence is legal or not.
|
||||
* This is not used here; it's just exported.
|
||||
*/
|
||||
Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd) {
|
||||
int length = trailingBytesForUTF8[*source]+1;
|
||||
if (source+length > sourceEnd) {
|
||||
return false;
|
||||
}
|
||||
return isLegalUTF8(source, length);
|
||||
}
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
ConversionResult ConvertUTF8toUTF16 (
|
||||
const UTF8** sourceStart, const UTF8* sourceEnd,
|
||||
UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
|
||||
ConversionResult result = conversionOK;
|
||||
const UTF8* source = *sourceStart;
|
||||
UTF16* target = *targetStart;
|
||||
while (source < sourceEnd) {
|
||||
UTF32 ch = 0;
|
||||
unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
|
||||
if (source + extraBytesToRead >= sourceEnd) {
|
||||
result = sourceExhausted; break;
|
||||
}
|
||||
/* Do this check whether lenient or strict */
|
||||
if (! isLegalUTF8(source, extraBytesToRead+1)) {
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
}
|
||||
/*
|
||||
* The cases all fall through. See "Note A" below.
|
||||
*/
|
||||
switch (extraBytesToRead) {
|
||||
case 5: ch += *source++; ch <<= 6; /* remember, illegal UTF-8 */
|
||||
case 4: ch += *source++; ch <<= 6; /* remember, illegal UTF-8 */
|
||||
case 3: ch += *source++; ch <<= 6;
|
||||
case 2: ch += *source++; ch <<= 6;
|
||||
case 1: ch += *source++; ch <<= 6;
|
||||
case 0: ch += *source++;
|
||||
}
|
||||
ch -= offsetsFromUTF8[extraBytesToRead];
|
||||
|
||||
if (target >= targetEnd) {
|
||||
source -= (extraBytesToRead+1); /* Back up source pointer! */
|
||||
result = targetExhausted; break;
|
||||
}
|
||||
if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */
|
||||
/* UTF-16 surrogate values are illegal in UTF-32 */
|
||||
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
|
||||
if (flags == strictConversion) {
|
||||
source -= (extraBytesToRead+1); /* return to the illegal value itself */
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
} else {
|
||||
*target++ = UNI_REPLACEMENT_CHAR;
|
||||
}
|
||||
} else {
|
||||
*target++ = (UTF16)ch; /* normal case */
|
||||
}
|
||||
} else if (ch > UNI_MAX_UTF16) {
|
||||
if (flags == strictConversion) {
|
||||
result = sourceIllegal;
|
||||
source -= (extraBytesToRead+1); /* return to the start */
|
||||
break; /* Bail out; shouldn't continue */
|
||||
} else {
|
||||
*target++ = UNI_REPLACEMENT_CHAR;
|
||||
}
|
||||
} else {
|
||||
/* target is a character in range 0xFFFF - 0x10FFFF. */
|
||||
if (target + 1 >= targetEnd) {
|
||||
source -= (extraBytesToRead+1); /* Back up source pointer! */
|
||||
result = targetExhausted; break;
|
||||
}
|
||||
ch -= halfBase;
|
||||
*target++ = (UTF16)((ch >> halfShift) + UNI_SUR_HIGH_START);
|
||||
*target++ = (UTF16)((ch & halfMask) + UNI_SUR_LOW_START);
|
||||
}
|
||||
}
|
||||
*sourceStart = source;
|
||||
*targetStart = target;
|
||||
return result;
|
||||
}
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
ConversionResult ConvertUTF32toUTF8 (
|
||||
const UTF32** sourceStart, const UTF32* sourceEnd,
|
||||
UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
|
||||
ConversionResult result = conversionOK;
|
||||
const UTF32* source = *sourceStart;
|
||||
UTF8* target = *targetStart;
|
||||
while (source < sourceEnd) {
|
||||
UTF32 ch;
|
||||
unsigned short bytesToWrite = 0;
|
||||
const UTF32 byteMask = 0xBF;
|
||||
const UTF32 byteMark = 0x80;
|
||||
ch = *source++;
|
||||
if (flags == strictConversion ) {
|
||||
/* UTF-16 surrogate values are illegal in UTF-32 */
|
||||
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
|
||||
--source; /* return to the illegal value itself */
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
}
|
||||
}
|
||||
/*
|
||||
* Figure out how many bytes the result will require. Turn any
|
||||
* illegally large UTF32 things (> Plane 17) into replacement chars.
|
||||
*/
|
||||
if (ch < (UTF32)0x80) { bytesToWrite = 1;
|
||||
} else if (ch < (UTF32)0x800) { bytesToWrite = 2;
|
||||
} else if (ch < (UTF32)0x10000) { bytesToWrite = 3;
|
||||
} else if (ch <= UNI_MAX_LEGAL_UTF32) { bytesToWrite = 4;
|
||||
} else { bytesToWrite = 3;
|
||||
ch = UNI_REPLACEMENT_CHAR;
|
||||
result = sourceIllegal;
|
||||
}
|
||||
|
||||
target += bytesToWrite;
|
||||
if (target > targetEnd) {
|
||||
--source; /* Back up source pointer! */
|
||||
target -= bytesToWrite; result = targetExhausted; break;
|
||||
}
|
||||
switch (bytesToWrite) { /* note: everything falls through. */
|
||||
case 4: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
|
||||
case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
|
||||
case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
|
||||
case 1: *--target = (UTF8) (ch | firstByteMark[bytesToWrite]);
|
||||
}
|
||||
target += bytesToWrite;
|
||||
}
|
||||
*sourceStart = source;
|
||||
*targetStart = target;
|
||||
return result;
|
||||
}
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
||||
|
||||
ConversionResult ConvertUTF8toUTF32 (
|
||||
const UTF8** sourceStart, const UTF8* sourceEnd,
|
||||
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
|
||||
ConversionResult result = conversionOK;
|
||||
const UTF8* source = *sourceStart;
|
||||
UTF32* target = *targetStart;
|
||||
while (source < sourceEnd) {
|
||||
UTF32 ch = 0;
|
||||
unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
|
||||
if (source + extraBytesToRead >= sourceEnd) {
|
||||
result = sourceExhausted; break;
|
||||
}
|
||||
/* Do this check whether lenient or strict */
|
||||
if (! isLegalUTF8(source, extraBytesToRead+1)) {
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
}
|
||||
/*
|
||||
* The cases all fall through. See "Note A" below.
|
||||
*/
|
||||
switch (extraBytesToRead) {
|
||||
case 5: ch += *source++; ch <<= 6;
|
||||
case 4: ch += *source++; ch <<= 6;
|
||||
case 3: ch += *source++; ch <<= 6;
|
||||
case 2: ch += *source++; ch <<= 6;
|
||||
case 1: ch += *source++; ch <<= 6;
|
||||
case 0: ch += *source++;
|
||||
}
|
||||
ch -= offsetsFromUTF8[extraBytesToRead];
|
||||
|
||||
if (target >= targetEnd) {
|
||||
source -= (extraBytesToRead+1); /* Back up the source pointer! */
|
||||
result = targetExhausted; break;
|
||||
}
|
||||
if (ch <= UNI_MAX_LEGAL_UTF32) {
|
||||
/*
|
||||
* UTF-16 surrogate values are illegal in UTF-32, and anything
|
||||
* over Plane 17 (> 0x10FFFF) is illegal.
|
||||
*/
|
||||
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
|
||||
if (flags == strictConversion) {
|
||||
source -= (extraBytesToRead+1); /* return to the illegal value itself */
|
||||
result = sourceIllegal;
|
||||
break;
|
||||
} else {
|
||||
*target++ = UNI_REPLACEMENT_CHAR;
|
||||
}
|
||||
} else {
|
||||
*target++ = ch;
|
||||
}
|
||||
} else { /* i.e., ch > UNI_MAX_LEGAL_UTF32 */
|
||||
result = sourceIllegal;
|
||||
*target++ = UNI_REPLACEMENT_CHAR;
|
||||
}
|
||||
}
|
||||
*sourceStart = source;
|
||||
*targetStart = target;
|
||||
return result;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
/* ---------------------------------------------------------------------
|
||||
|
||||
Note A.
|
||||
The fall-through switches in UTF-8 reading code save a
|
||||
temp variable, some decrements & conditionals. The switches
|
||||
are equivalent to the following loop:
|
||||
{
|
||||
int tmpBytesToRead = extraBytesToRead+1;
|
||||
do {
|
||||
ch += *source++;
|
||||
--tmpBytesToRead;
|
||||
if (tmpBytesToRead) ch <<= 6;
|
||||
} while (tmpBytesToRead > 0);
|
||||
}
|
||||
In UTF-8 writing code, the switches on "bytesToWrite" are
|
||||
similarly unrolled loops.
|
||||
|
||||
--------------------------------------------------------------------- */
|
162
src/linenoise/ConvertUTF.h
Executable file
162
src/linenoise/ConvertUTF.h
Executable file
|
@ -0,0 +1,162 @@
|
|||
/*
|
||||
* Copyright 2001-2004 Unicode, Inc.
|
||||
*
|
||||
* Disclaimer
|
||||
*
|
||||
* This source code is provided as is by Unicode, Inc. No claims are
|
||||
* made as to fitness for any particular purpose. No warranties of any
|
||||
* kind are expressed or implied. The recipient agrees to determine
|
||||
* applicability of information provided. If this file has been
|
||||
* purchased on magnetic or optical media from Unicode, Inc., the
|
||||
* sole remedy for any claim will be exchange of defective media
|
||||
* within 90 days of receipt.
|
||||
*
|
||||
* Limitations on Rights to Redistribute This Code
|
||||
*
|
||||
* Unicode, Inc. hereby grants the right to freely use the information
|
||||
* supplied in this file in the creation of products supporting the
|
||||
* Unicode Standard, and to make copies of this file in any form
|
||||
* for internal or external distribution as long as this notice
|
||||
* remains attached.
|
||||
*/
|
||||
|
||||
/* ---------------------------------------------------------------------
|
||||
|
||||
Conversions between UTF32, UTF-16, and UTF-8. Header file.
|
||||
|
||||
Several funtions are included here, forming a complete set of
|
||||
conversions between the three formats. UTF-7 is not included
|
||||
here, but is handled in a separate source file.
|
||||
|
||||
Each of these routines takes pointers to input buffers and output
|
||||
buffers. The input buffers are const.
|
||||
|
||||
Each routine converts the text between *sourceStart and sourceEnd,
|
||||
putting the result into the buffer between *targetStart and
|
||||
targetEnd. Note: the end pointers are *after* the last item: e.g.
|
||||
*(sourceEnd - 1) is the last item.
|
||||
|
||||
The return result indicates whether the conversion was successful,
|
||||
and if not, whether the problem was in the source or target buffers.
|
||||
(Only the first encountered problem is indicated.)
|
||||
|
||||
After the conversion, *sourceStart and *targetStart are both
|
||||
updated to point to the end of last text successfully converted in
|
||||
the respective buffers.
|
||||
|
||||
Input parameters:
|
||||
sourceStart - pointer to a pointer to the source buffer.
|
||||
The contents of this are modified on return so that
|
||||
it points at the next thing to be converted.
|
||||
targetStart - similarly, pointer to pointer to the target buffer.
|
||||
sourceEnd, targetEnd - respectively pointers to the ends of the
|
||||
two buffers, for overflow checking only.
|
||||
|
||||
These conversion functions take a ConversionFlags argument. When this
|
||||
flag is set to strict, both irregular sequences and isolated surrogates
|
||||
will cause an error. When the flag is set to lenient, both irregular
|
||||
sequences and isolated surrogates are converted.
|
||||
|
||||
Whether the flag is strict or lenient, all illegal sequences will cause
|
||||
an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
|
||||
or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
|
||||
must check for illegal sequences.
|
||||
|
||||
When the flag is set to lenient, characters over 0x10FFFF are converted
|
||||
to the replacement character; otherwise (when the flag is set to strict)
|
||||
they constitute an error.
|
||||
|
||||
Output parameters:
|
||||
The value "sourceIllegal" is returned from some routines if the input
|
||||
sequence is malformed. When "sourceIllegal" is returned, the source
|
||||
value will point to the illegal value that caused the problem. E.g.,
|
||||
in UTF-8 when a sequence is malformed, it points to the start of the
|
||||
malformed sequence.
|
||||
|
||||
Author: Mark E. Davis, 1994.
|
||||
Rev History: Rick McGowan, fixes & updates May 2001.
|
||||
Fixes & updates, Sept 2001.
|
||||
|
||||
------------------------------------------------------------------------ */
|
||||
|
||||
/* ---------------------------------------------------------------------
|
||||
The following 4 definitions are compiler-specific.
|
||||
The C standard does not guarantee that wchar_t has at least
|
||||
16 bits, so wchar_t is no less portable than unsigned short!
|
||||
All should be unsigned values to avoid sign extension during
|
||||
bit mask & shift operations.
|
||||
------------------------------------------------------------------------ */
|
||||
|
||||
#if 0
|
||||
typedef unsigned long UTF32; /* at least 32 bits */
|
||||
typedef unsigned short UTF16; /* at least 16 bits */
|
||||
typedef unsigned char UTF8; /* typically 8 bits */
|
||||
#endif
|
||||
|
||||
#include <stdint.h>
|
||||
#include <string>
|
||||
|
||||
namespace linenoise_ng {
|
||||
|
||||
typedef uint32_t UTF32;
|
||||
typedef uint16_t UTF16;
|
||||
typedef uint8_t UTF8;
|
||||
typedef unsigned char Boolean; /* 0 or 1 */
|
||||
|
||||
/* Some fundamental constants */
|
||||
#define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
|
||||
#define UNI_MAX_BMP (UTF32)0x0000FFFF
|
||||
#define UNI_MAX_UTF16 (UTF32)0x0010FFFF
|
||||
#define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
|
||||
#define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
|
||||
|
||||
typedef enum {
|
||||
conversionOK, /* conversion successful */
|
||||
sourceExhausted, /* partial character in source, but hit end */
|
||||
targetExhausted, /* insuff. room in target for conversion */
|
||||
sourceIllegal /* source sequence is illegal/malformed */
|
||||
} ConversionResult;
|
||||
|
||||
typedef enum {
|
||||
strictConversion = 0,
|
||||
lenientConversion
|
||||
} ConversionFlags;
|
||||
|
||||
// /* This is for C++ and does no harm in C */
|
||||
// #ifdef __cplusplus
|
||||
// extern "C" {
|
||||
// #endif
|
||||
|
||||
ConversionResult ConvertUTF8toUTF16 (
|
||||
const UTF8** sourceStart, const UTF8* sourceEnd,
|
||||
UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
|
||||
|
||||
ConversionResult ConvertUTF16toUTF8 (
|
||||
const UTF16** sourceStart, const UTF16* sourceEnd,
|
||||
UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
|
||||
|
||||
ConversionResult ConvertUTF8toUTF32 (
|
||||
const UTF8** sourceStart, const UTF8* sourceEnd,
|
||||
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
|
||||
|
||||
ConversionResult ConvertUTF32toUTF8 (
|
||||
const UTF32** sourceStart, const UTF32* sourceEnd,
|
||||
UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
|
||||
|
||||
ConversionResult ConvertUTF16toUTF32 (
|
||||
const UTF16** sourceStart, const UTF16* sourceEnd,
|
||||
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
|
||||
|
||||
ConversionResult ConvertUTF32toUTF16 (
|
||||
const UTF32** sourceStart, const UTF32* sourceEnd,
|
||||
char16_t** targetStart, char16_t* targetEnd, ConversionFlags flags);
|
||||
|
||||
Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
|
||||
|
||||
// #ifdef __cplusplus
|
||||
// }
|
||||
// #endif
|
||||
|
||||
}
|
||||
|
||||
/* --------------------------------------------------------------------- */
|
|
@ -1,5 +1,8 @@
|
|||
Copyright (c) 2010-2014, Salvatore Sanfilippo <antirez at gmail dot com>
|
||||
Copyright (c) 2010-2013, Pieter Noordhuis <pcnoordhuis at gmail dot com>
|
||||
linenoise.cpp
|
||||
=============
|
||||
|
||||
Copyright (c) 2010, Salvatore Sanfilippo <antirez at gmail dot com>
|
||||
Copyright (c) 2010, Pieter Noordhuis <pcnoordhuis at gmail dot com>
|
||||
|
||||
All rights reserved.
|
||||
|
||||
|
@ -8,18 +11,56 @@ modification, are permitted provided that the following conditions are met:
|
|||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
* Neither the name of Redis nor the names of its contributors may be used
|
||||
to endorse or promote products derived from this software without
|
||||
specific prior written permission.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright notice,
|
||||
this list of conditions and the following disclaimer in the documentation
|
||||
and/or other materials provided with the distribution.
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
||||
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
||||
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
||||
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
|
||||
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
||||
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
||||
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
|
||||
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
||||
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
wcwidth.cpp
|
||||
===========
|
||||
|
||||
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.
|
||||
|
||||
|
||||
|
||||
ConvertUTF.cpp
|
||||
==============
|
||||
|
||||
Copyright 2001-2004 Unicode, Inc.
|
||||
|
||||
Disclaimer
|
||||
|
||||
This source code is provided as is by Unicode, Inc. No claims are
|
||||
made as to fitness for any particular purpose. No warranties of any
|
||||
kind are expressed or implied. The recipient agrees to determine
|
||||
applicability of information provided. If this file has been
|
||||
purchased on magnetic or optical media from Unicode, Inc., the
|
||||
sole remedy for any claim will be exchange of defective media
|
||||
within 90 days of receipt.
|
||||
|
||||
Limitations on Rights to Redistribute This Code
|
||||
|
||||
Unicode, Inc. hereby grants the right to freely use the information
|
||||
supplied in this file in the creation of products supporting the
|
||||
Unicode Standard, and to make copies of this file in any form
|
||||
for internal or external distribution as long as this notice
|
||||
remains attached.
|
||||
|
|
File diff suppressed because it is too large
Load diff
3457
src/linenoise/linenoise.cpp
Normal file
3457
src/linenoise/linenoise.cpp
Normal file
File diff suppressed because it is too large
Load diff
|
@ -1,70 +1,70 @@
|
|||
/* linenoise.h -- VERSION 1.0
|
||||
*
|
||||
* Guerrilla line editing library against the idea that a line editing lib
|
||||
* needs to be 20,000 lines of C code.
|
||||
/* linenoise.h -- guerrilla line editing library against the idea that a
|
||||
* line editing lib needs to be 20,000 lines of C code.
|
||||
*
|
||||
* See linenoise.c for more information.
|
||||
*
|
||||
* ------------------------------------------------------------------------
|
||||
*
|
||||
* Copyright (c) 2010-2014, Salvatore Sanfilippo <antirez at gmail dot com>
|
||||
* Copyright (c) 2010-2013, Pieter Noordhuis <pcnoordhuis at gmail dot com>
|
||||
* Copyright (c) 2010, Salvatore Sanfilippo <antirez at gmail dot com>
|
||||
* Copyright (c) 2010, Pieter Noordhuis <pcnoordhuis at gmail dot com>
|
||||
*
|
||||
* All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions are
|
||||
* met:
|
||||
*
|
||||
* * Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* modification, are permitted provided that the following conditions are met:
|
||||
*
|
||||
* * Redistributions of source code must retain the above copyright notice,
|
||||
* this list of conditions and the following disclaimer.
|
||||
* * Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in the
|
||||
* documentation and/or other materials provided with the distribution.
|
||||
* * Neither the name of Redis nor the names of its contributors may be used
|
||||
* to endorse or promote products derived from this software without
|
||||
* specific prior written permission.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
* HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
||||
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
||||
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
* POSSIBILITY OF SUCH DAMAGE.
|
||||
*/
|
||||
|
||||
#ifndef __LINENOISE_H
|
||||
#define __LINENOISE_H
|
||||
|
||||
#define LINENOISE_VERSION "1.0.0"
|
||||
#define LINENOISE_VERSION_MAJOR 1
|
||||
#define LINENOISE_VERSION_MINOR 1
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
typedef struct linenoiseCompletions {
|
||||
size_t len;
|
||||
char **cvec;
|
||||
} linenoiseCompletions;
|
||||
typedef struct linenoiseCompletions linenoiseCompletions;
|
||||
|
||||
typedef void(linenoiseCompletionCallback)(const char*, linenoiseCompletions*);
|
||||
typedef char*(linenoiseHintsCallback)(const char *, int *color, int *bold);
|
||||
typedef void(linenoiseFreeHintsCallback)(void *);
|
||||
void linenoiseSetCompletionCallback(linenoiseCompletionCallback *);
|
||||
void linenoiseSetHintsCallback(linenoiseHintsCallback *);
|
||||
void linenoiseSetFreeHintsCallback(linenoiseFreeHintsCallback *);
|
||||
void linenoiseAddCompletion(linenoiseCompletions *, const char *);
|
||||
void linenoiseSetCompletionCallback(linenoiseCompletionCallback* fn);
|
||||
void linenoiseAddCompletion(linenoiseCompletions* lc, const char* str);
|
||||
|
||||
char* linenoise(const char* prompt);
|
||||
void linenoiseFree(void *ptr);
|
||||
void linenoisePreloadBuffer(const char* preloadText);
|
||||
int linenoiseHistoryAdd(const char* line);
|
||||
int linenoiseHistorySetMaxLen(int len);
|
||||
char* linenoiseHistoryLine(int index);
|
||||
int linenoiseHistorySave(const char* filename);
|
||||
int linenoiseHistoryLoad(const char* filename);
|
||||
void linenoiseHistoryFree(void);
|
||||
void linenoiseClearScreen(void);
|
||||
void linenoiseSetMultiLine(int ml);
|
||||
void linenoisePrintKeyCodes(void);
|
||||
/* the following are extensions to the original linenoise API */
|
||||
int linenoiseInstallWindowChangeHandler(void);
|
||||
/* returns type of key pressed: 1 = CTRL-C, 2 = CTRL-D, 0 = other */
|
||||
int linenoiseKeyType(void);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
|
|
315
src/linenoise/wcwidth.cpp
Normal file
315
src/linenoise/wcwidth.cpp
Normal file
|
@ -0,0 +1,315 @@
|
|||
/*
|
||||
* 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>
|
||||
#include <string>
|
||||
#include <memory>
|
||||
|
||||
namespace linenoise_ng {
|
||||
|
||||
struct interval {
|
||||
char32_t first;
|
||||
char32_t last;
|
||||
};
|
||||
|
||||
/* auxiliary function for binary search in interval table */
|
||||
static int bisearch(char32_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(char32_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 char32_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;
|
||||
}
|
||||
|
||||
}
|
|
@ -2,7 +2,7 @@ programs += nix
|
|||
|
||||
nix_DIR := $(d)
|
||||
|
||||
nix_SOURCES := $(wildcard $(d)/*.cc) src/linenoise/linenoise.c
|
||||
nix_SOURCES := $(wildcard $(d)/*.cc) $(wildcard src/linenoise/*.cpp)
|
||||
|
||||
nix_LIBS = libexpr libmain libstore libutil libformat
|
||||
|
||||
|
|
|
@ -185,7 +185,7 @@ void NixRepl::mainLoop(const std::vector<std::string> & files)
|
|||
bool NixRepl::getLine(string & input, const std::string &prompt)
|
||||
{
|
||||
char * s = linenoise(prompt.c_str());
|
||||
Finally doFree([&]() { linenoiseFree(s); });
|
||||
Finally doFree([&]() { free(s); });
|
||||
if (!s) return false;
|
||||
input += s;
|
||||
return true;
|
||||
|
|
Loading…
Reference in a new issue