taynpg/fanyi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

init:初始可用版本

Browse Source
This commit is contained in:
taynpg 2025-01-06 13:31:00 +08:00
commit 8577aea96b
15 changed files with 29794 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
.clang-format Normal file
View File

@ -0,0 +1,17 @@
BasedOnStyle: LLVM
IndentWidth: 4
PointerAlignment: Left
AccessModifierOffset: -4
BreakBeforeBraces: Custom
BraceWrapping:
AfterFunction: true
AfterClass: true
Cpp11BracedListStyle: true
ReflowComments: true
SpacesBeforeTrailingComments: 3
TabWidth: 4
ConstructorInitializerAllOnOneLineOrOnePerLine: true
ColumnLimit: 130
AllowShortBlocksOnASingleLine: Never
AllowShortFunctionsOnASingleLine: None
AllowShortEnumsOnASingleLine: false

4
.gitignore vendored Normal file
View File

@ -0,0 +1,4 @@
build
.vs
.cache
cmake-*

111
.vscode/settings.json vendored Normal file
View File

@ -0,0 +1,111 @@
{
"files.autoSave": "onFocusChange",
"editor.fontSize": 14,
"editor.fontFamily": "'Source Code Pro', 'Courier New', monospace",
"terminal.integrated.fontFamily": "Source Code Pro",
"cmake.configureOnOpen": true,
"cmake.debugConfig": {
"console": "integratedTerminal",
"setupCommands": [
{
"description": "-gdb-set charset utf-8",
"text": "-gdb-set charset UTF-8"
},
{
"description": "Enable gdb pretty-printing",
"text": "-enable-pretty-printing",
"ignoreFailures": true
}
],
"args": [
"test.txt"
]
},
// "cmake.configureSettings": {
// "CMAKE_TOOLCHAIN_FILE": "${env:VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake"
// },
"cmake.options.statusBarVisibility": "visible",
"cmake.generator": "Ninja",
"C_Cpp.default.compileCommands": "${workspaceRoot}/build/compile_commands.json",
"C_Cpp.default.cppStandard": "c++17",
"C_Cpp.default.configurationProvider": "ms-vscode.cmake-tools",
"editor.inlayHints.enabled": "off",
"editor.unicodeHighlight.allowedLocales": {
"ja": true,
"zh-hant": true,
"zh-hans": true
},
"files.associations": {
"string": "cpp",
"ostream": "cpp",
"array": "cpp",
"atomic": "cpp",
"bit": "cpp",
"*.tcc": "cpp",
"bitset": "cpp",
"cctype": "cpp",
"clocale": "cpp",
"cmath": "cpp",
"compare": "cpp",
"concepts": "cpp",
"condition_variable": "cpp",
"csignal": "cpp",
"cstdarg": "cpp",
"cstddef": "cpp",
"cstdint": "cpp",
"cstdio": "cpp",
"cstdlib": "cpp",
"cstring": "cpp",
"ctime": "cpp",
"cwchar": "cpp",
"cwctype": "cpp",
"deque": "cpp",
"list": "cpp",
"map": "cpp",
"set": "cpp",
"unordered_map": "cpp",
"unordered_set": "cpp",
"vector": "cpp",
"exception": "cpp",
"algorithm": "cpp",
"functional": "cpp",
"iterator": "cpp",
"memory": "cpp",
"memory_resource": "cpp",
"numeric": "cpp",
"optional": "cpp",
"random": "cpp",
"ratio": "cpp",
"regex": "cpp",
"string_view": "cpp",
"system_error": "cpp",
"tuple": "cpp",
"type_traits": "cpp",
"utility": "cpp",
"fstream": "cpp",
"initializer_list": "cpp",
"iomanip": "cpp",
"iosfwd": "cpp",
"iostream": "cpp",
"istream": "cpp",
"limits": "cpp",
"mutex": "cpp",
"new": "cpp",
"numbers": "cpp",
"semaphore": "cpp",
"sstream": "cpp",
"stdexcept": "cpp",
"stop_token": "cpp",
"streambuf": "cpp",
"thread": "cpp",
"cinttypes": "cpp",
"typeinfo": "cpp",
"any": "cpp",
"codecvt": "cpp",
"forward_list": "cpp",
"ranges": "cpp",
"span": "cpp",
"valarray": "cpp",
"variant": "cpp"
}
}

539
3rd/ConvertUTF.c Normal file
View File

@ -0,0 +1,539 @@
/*
* 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
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,
UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
ConversionResult result = conversionOK;
const UTF32* source = *sourceStart;
UTF16* 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 sequences
* 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.
--------------------------------------------------------------------- */

149
3rd/ConvertUTF.h Normal file
View File

@ -0,0 +1,149 @@
/*
* 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 functions 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.
------------------------------------------------------------------------ */
typedef unsigned int UTF32; /* at least 32 bits */
typedef unsigned short UTF16; /* at least 16 bits */
typedef unsigned char UTF8; /* typically 8 bits */
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, /* insufficient 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,
UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
#ifdef __cplusplus
}
#endif
/* --------------------------------------------------------------------- */

3630
3rd/SimpleIni.h Normal file
View File

File diff suppressed because it is too large Load Diff

30
3rd/client.log Normal file
View File

@ -0,0 +1,30 @@
[2025-01-06 12:09:57.936][info]: Configure At 2025-01-06 09:18 under 3d34371 on main
[2025-01-06 12:09:57.954][info]: Connected to 106.14.150.219:9898
[2025-01-06 12:09:57.954][warning]: SupportCmd:Get|Up|Down|Cancel|Update
[2025-01-06 12:09:57.975][debug]: Your ID:223.112.40.246:43706
[2025-01-06 12:09:58.744][debug]: *****************************************
[2025-01-06 12:09:58.744][info]: [1][101.251.238.60:51971][2025-01-04 00:06:11][]
[2025-01-06 12:09:58.744][debug]: *****************************************
[2025-01-06 12:09:58.744][info]: [2][101.251.238.60:54233][2025-01-04 00:06:20][]
[2025-01-06 12:09:58.744][debug]: *****************************************
[2025-01-06 12:09:58.744][info]: [3][185.147.124.64:63117][2025-01-05 14:22:58][]
[2025-01-06 12:09:58.744][debug]: *****************************************
[2025-01-06 12:09:58.744][info]: [4][223.112.40.246:43706][2025-01-06 12:09:58][]
[2025-01-06 12:09:58.744][debug]: *****************************************
[2025-01-06 12:09:58.744][info]: [5][223.112.40.246:51843][2025-01-06 12:09:21][2025-01-06 12:09:42]
[2025-01-06 12:09:58.744][info]: FILE ==> D:\git\transm\3rd\ConvertUTF.h
[2025-01-06 12:09:58.744][info]: FILE ==> D:\git\transm\3rd\ConvertUTF.c
[2025-01-06 12:09:58.744][info]: FILE ==> D:\git\transm\3rd\SimpleIni.h
[2025-01-06 12:09:58.744][debug]: *****************************************
[2025-01-06 12:09:58.744][info]: [6][223.112.40.246:54579][2025-01-06 09:21:07][2025-01-06 09:36:00]
[2025-01-06 12:09:58.744][info]: FILE ==> C:\Users\tang.yunpeng\Downloads\Clash.Verge_2.0.2_amd64.deb
[2025-01-06 12:10:04.170][warning]: Start Down => D:\git\transm\3rd\ConvertUTF.h To /home/yun/Documents/fanyi/3rd/ConvertUTF.h
[2025-01-06 12:10:04.232][warning]: Trans done, close file /home/yun/Documents/fanyi/3rd/ConvertUTF.h.
[2025-01-06 12:10:06.223][warning]: Start Down => D:\git\transm\3rd\ConvertUTF.c To /home/yun/Documents/fanyi/3rd/ConvertUTF.c
[2025-01-06 12:10:06.295][warning]: Trans done, close file /home/yun/Documents/fanyi/3rd/ConvertUTF.c.
[2025-01-06 12:10:08.278][warning]: Start Down => D:\git\transm\3rd\SimpleIni.h To /home/yun/Documents/fanyi/3rd/SimpleIni.h
[2025-01-06 12:10:08.388][warning]: Trans done, close file /home/yun/Documents/fanyi/3rd/SimpleIni.h.
[2025-01-06 12:10:12.812][info]: Disconnected.
[2025-01-06 12:10:12.812][error]: operator() 125 error => Operation aborted.
[2025-01-06 12:10:12.812][info]: run exit.
[2025-01-06 12:10:12.812][info]: exit &&&&&&&&&&&&&

24765
3rd/nlohmann/json.hpp Normal file
View File

File diff suppressed because it is too large Load Diff

176
3rd/nlohmann/json_fwd.hpp Normal file
View File

@ -0,0 +1,176 @@
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.11.3
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2023 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#ifndef INCLUDE_NLOHMANN_JSON_FWD_HPP_
#define INCLUDE_NLOHMANN_JSON_FWD_HPP_
#include <cstdint> // int64_t, uint64_t
#include <map> // map
#include <memory> // allocator
#include <string> // string
#include <vector> // vector
// #include <nlohmann/detail/abi_macros.hpp>
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.11.3
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2023 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
// This file contains all macro definitions affecting or depending on the ABI
#ifndef JSON_SKIP_LIBRARY_VERSION_CHECK
#if defined(NLOHMANN_JSON_VERSION_MAJOR) && defined(NLOHMANN_JSON_VERSION_MINOR) && defined(NLOHMANN_JSON_VERSION_PATCH)
#if NLOHMANN_JSON_VERSION_MAJOR != 3 || NLOHMANN_JSON_VERSION_MINOR != 11 || NLOHMANN_JSON_VERSION_PATCH != 3
#warning "Already included a different version of the library!"
#endif
#endif
#endif
#define NLOHMANN_JSON_VERSION_MAJOR 3 // NOLINT(modernize-macro-to-enum)
#define NLOHMANN_JSON_VERSION_MINOR 11 // NOLINT(modernize-macro-to-enum)
#define NLOHMANN_JSON_VERSION_PATCH 3 // NOLINT(modernize-macro-to-enum)
#ifndef JSON_DIAGNOSTICS
#define JSON_DIAGNOSTICS 0
#endif
#ifndef JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
#define JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON 0
#endif
#if JSON_DIAGNOSTICS
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTICS _diag
#else
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTICS
#endif
#if JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
#define NLOHMANN_JSON_ABI_TAG_LEGACY_DISCARDED_VALUE_COMPARISON _ldvcmp
#else
#define NLOHMANN_JSON_ABI_TAG_LEGACY_DISCARDED_VALUE_COMPARISON
#endif
#ifndef NLOHMANN_JSON_NAMESPACE_NO_VERSION
#define NLOHMANN_JSON_NAMESPACE_NO_VERSION 0
#endif
// Construct the namespace ABI tags component
#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b) json_abi ## a ## b
#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b) \
NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b)
#define NLOHMANN_JSON_ABI_TAGS \
NLOHMANN_JSON_ABI_TAGS_CONCAT( \
NLOHMANN_JSON_ABI_TAG_DIAGNOSTICS, \
NLOHMANN_JSON_ABI_TAG_LEGACY_DISCARDED_VALUE_COMPARISON)
// Construct the namespace version component
#define NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT_EX(major, minor, patch) \
_v ## major ## _ ## minor ## _ ## patch
#define NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT(major, minor, patch) \
NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT_EX(major, minor, patch)
#if NLOHMANN_JSON_NAMESPACE_NO_VERSION
#define NLOHMANN_JSON_NAMESPACE_VERSION
#else
#define NLOHMANN_JSON_NAMESPACE_VERSION \
NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT(NLOHMANN_JSON_VERSION_MAJOR, \
NLOHMANN_JSON_VERSION_MINOR, \
NLOHMANN_JSON_VERSION_PATCH)
#endif
// Combine namespace components
#define NLOHMANN_JSON_NAMESPACE_CONCAT_EX(a, b) a ## b
#define NLOHMANN_JSON_NAMESPACE_CONCAT(a, b) \
NLOHMANN_JSON_NAMESPACE_CONCAT_EX(a, b)
#ifndef NLOHMANN_JSON_NAMESPACE
#define NLOHMANN_JSON_NAMESPACE \
nlohmann::NLOHMANN_JSON_NAMESPACE_CONCAT( \
NLOHMANN_JSON_ABI_TAGS, \
NLOHMANN_JSON_NAMESPACE_VERSION)
#endif
#ifndef NLOHMANN_JSON_NAMESPACE_BEGIN
#define NLOHMANN_JSON_NAMESPACE_BEGIN \
namespace nlohmann \
{ \
inline namespace NLOHMANN_JSON_NAMESPACE_CONCAT( \
NLOHMANN_JSON_ABI_TAGS, \
NLOHMANN_JSON_NAMESPACE_VERSION) \
{
#endif
#ifndef NLOHMANN_JSON_NAMESPACE_END
#define NLOHMANN_JSON_NAMESPACE_END \
} /* namespace (inline namespace) NOLINT(readability/namespace) */ \
} // namespace nlohmann
#endif
/*!
@brief namespace for Niels Lohmann
@see https://github.com/nlohmann
@since version 1.0.0
*/
NLOHMANN_JSON_NAMESPACE_BEGIN
/*!
@brief default JSONSerializer template argument
This serializer ignores the template arguments and uses ADL
([argument-dependent lookup](https://en.cppreference.com/w/cpp/language/adl))
for serialization.
*/
template<typename T = void, typename SFINAE = void>
struct adl_serializer;
/// a class to store JSON values
/// @sa https://json.nlohmann.me/api/basic_json/
template<template<typename U, typename V, typename... Args> class ObjectType =
std::map,
template<typename U, typename... Args> class ArrayType = std::vector,
class StringType = std::string, class BooleanType = bool,
class NumberIntegerType = std::int64_t,
class NumberUnsignedType = std::uint64_t,
class NumberFloatType = double,
template<typename U> class AllocatorType = std::allocator,
template<typename T, typename SFINAE = void> class JSONSerializer =
adl_serializer,
class BinaryType = std::vector<std::uint8_t>, // cppcheck-suppress syntaxError
class CustomBaseClass = void>
class basic_json;
/// @brief JSON Pointer defines a string syntax for identifying a specific value within a JSON document
/// @sa https://json.nlohmann.me/api/json_pointer/
template<typename RefStringType>
class json_pointer;
/*!
@brief default specialization
@sa https://json.nlohmann.me/api/json/
*/
using json = basic_json<>;
/// @brief a minimal map-like container that preserves insertion order
/// @sa https://json.nlohmann.me/api/ordered_map/
template<class Key, class T, class IgnoredLess, class Allocator>
struct ordered_map;
/// @brief specialization that maintains the insertion order of object keys
/// @sa https://json.nlohmann.me/api/ordered_json/
using ordered_json = basic_json<nlohmann::ordered_map>;
NLOHMANN_JSON_NAMESPACE_END
#endif // INCLUDE_NLOHMANN_JSON_FWD_HPP_

28
CMakeLists.txt Normal file
View File

@ -0,0 +1,28 @@
cmake_minimum_required(VERSION 3.16)
project(fanyi LANGUAGES CXX)
set(CMAKE_CXX_STANDARD 17)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
if (MSVC)
add_compile_options(/source-charset:utf-8)
endif()
if (CMAKE_CXX_COMPILER_ID MATCHES "GNU" AND CMAKE_SYSTEM_NAME MATCHES "Windows")
MESSAGE(STATUS "Add MinGW Param.")
add_compile_options(-finput-charset=utf-8)
add_compile_options(-fexec-charset=gbk)
endif()
set(CMAKE_DEBUG_POSTFIX "d")
message(STATUS "System: ${CMAKE_SYSTEM_NAME}")
message(STATUS "Compiler CXX ID: ${CMAKE_CXX_COMPILER_ID}")
set(LIBRARY_OUTPUT_PATH ${PROJECT_BINARY_DIR}/lib/${CMAKE_BUILD_TYPE})
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/bin/${CMAKE_BUILD_TYPE}/)
include_directories(3rd)
find_package(CURL REQUIRED)
find_package(OpenSSL REQUIRED)
add_executable(fanyi main.cpp handle.h handle.cpp)
target_link_libraries(fanyi CURL::libcurl OpenSSL::SSL OpenSSL::Crypto xlnt)

20
README.md Normal file
View File

@ -0,0 +1,20 @@
# 说明
使用百度翻译API将中文翻译为英文。
# 注意
windows下需要特殊处理编码问题（API要求为UTF-8）。
# 输入格式
- 在程序所在位置下，读取`fanyi.ini`配置文件（请参考模板），设置百度翻译`API`相关信息。
- 命令行第二个参数，读取一个txt文件，每一行是一句要翻译的内容。
# 依赖
- 依赖`openssl`生成`md5`。
- 依赖`libcurl`访问`https`。
- 依赖[xlnt](https://github.com/tfussell/xlnt)生成`xlsx`。
对于`Debian`系列系统，示例安装`sudo apt install libssl-dev libcurl4-openssl-dev`。

4
fanyi.ini Normal file
View File

@ -0,0 +1,4 @@
[Config]
BaseURL = https://fanyi-api.baidu.com/api/trans/vip/translate?
AppID =
SecretID =

158
handle.cpp Normal file
View File

@ -0,0 +1,158 @@
#include "handle.h"
#include <iomanip>
#include <iostream>
#include <random>
#include <sstream>
#include <SimpleIni.h>
CHttpsHandle::CHttpsHandle()
{
curl_global_init(CURL_GLOBAL_DEFAULT);
curl = curl_easy_init();
}
CHttpsHandle::~CHttpsHandle()
{
if (curl) {
curl_easy_cleanup(curl);
}
curl_global_cleanup();
}
std::string CHttpsHandle::sendGetRequest(const std::string& url)
{
// 用于保存响应数据
std::string response_data;
if (curl) {
// 设置请求 URL
curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
curl_easy_setopt(curl, CURLOPT_POST, 0L);
// 设置回调函数，用于获取响应数据
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, WriteCallback);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, &response_data);
// 设置不验证 SSL 证书（如果使用自签名证书或测试环境时可以忽略）
curl_easy_setopt(curl, CURLOPT_SSL_VERIFYPEER, 0L); // 忽略 SSL 证书验证
curl_easy_setopt(curl, CURLOPT_SSL_VERIFYHOST, 0L); // 忽略主机名验证
// 执行请求
CURLcode res = curl_easy_perform(curl);
// 检查请求是否成功
if (res != CURLE_OK) {
std::cerr << "curl_easy_perform() failed: " << curl_easy_strerror(res) << std::endl;
return "";
}
}
return response_data;
}
size_t CHttpsHandle::WriteCallback(void* contents, size_t size, size_t nmemb, void* userp)
{
size_t total_size = size * nmemb;
std::string* response_data = (std::string*)userp;
response_data->append((char*)contents, total_size);
return total_size;
}
std::string CUtil::generateMD5(const std::string& input)
{
EVP_MD_CTX* mdctx = EVP_MD_CTX_new();
if (mdctx == nullptr) {
std::cerr << "Error creating MD5 context!" << std::endl;
return "";
}
if (EVP_DigestInit_ex(mdctx, EVP_md5(), nullptr) != 1) {
std::cerr << "Error initializing MD5!" << std::endl;
EVP_MD_CTX_free(mdctx);
return "";
}
if (EVP_DigestUpdate(mdctx, input.c_str(), input.length()) != 1) {
std::cerr << "Error updating MD5!" << std::endl;
EVP_MD_CTX_free(mdctx);
return "";
}
unsigned char md_value[EVP_MAX_MD_SIZE];
unsigned int md_len = 0;
if (EVP_DigestFinal_ex(mdctx, md_value, &md_len) != 1) {
std::cerr << "Error finalizing MD5!" << std::endl;
EVP_MD_CTX_free(mdctx);
return "";
}
EVP_MD_CTX_free(mdctx);
std::ostringstream md5String;
for (unsigned int i = 0; i < md_len; ++i) {
md5String << std::setw(2) << std::setfill('0') << std::hex << (int)md_value[i];
}
return md5String.str();
}
std::string CUtil::generateRandomNumStr()
{
std::random_device rd;
std::mt19937 gen(rd());
std::uniform_int_distribution<> dis(100000000, 999999999);
long long random_number = dis(gen);
return std::to_string(random_number);
}
void CTransTool::set_id(const str_t& id, const str_t& secret_key)
{
appid_ = id;
secret_key_ = secret_key;
}
std::string CTransTool::combine(const str_t& words, const str_t& from, const str_t& to)
{
char* buffer = new char[2048];
std::string radom_str = CUtil::generateRandomNumStr();
std::string str1 = appid_ + words + radom_str + secret_key_;
std::string md5 = CUtil::generateMD5(str1);
std::string req_word = CUtil::urlEncode(words);
std::snprintf(buffer, 2048, "q=%s&from=%s&to=%s&appid=%s&salt=%s&sign=%s", req_word.c_str(), from.c_str(),
to.c_str(), appid_.c_str(), radom_str.c_str(), md5.c_str());
std::string source_pre(buffer);
delete[] buffer;
return source_pre;
}
std::string CUtil::urlEncode(const std::string& str)
{
std::ostringstream encoded;
for (unsigned char c : str) {
if (std::isalnum(c) || c == '-' || c == '_' || c == '.' || c == '~') {
encoded << c;
} else {
encoded << '%' << std::uppercase << std::setw(2) << std::setfill('0') << std::hex << (int)c;
}
}
return encoded.str();
}
bool CConfig::parse_config(ConfigInfo& config, const std::string& config_path)
{
CSimpleIniA ini_handle{};
SI_Error ret = ini_handle.LoadFile(config_path.c_str());
if (ret != SI_OK) {
return false;
}
if (!ini_handle.KeyExists("Config", "BaseURL")) {
std::cerr << "Not Key Found Config/BaseURL in fanyi.ini" << std::endl;
return false;
}
config.baseUrl = ini_handle.GetValue("Config", "BaseURL");
if (!ini_handle.KeyExists("Config", "AppID")) {
std::cerr << "Not Key Found Config/AppID in fanyi.ini" << std::endl;
return false;
}
config.appID = ini_handle.GetValue("Config", "AppID");
if (!ini_handle.KeyExists("Config", "SecretID")) {
std::cerr << "Not Key Found Config/SecretID in fanyi.ini" << std::endl;
return false;
}
config.secretID = ini_handle.GetValue("Config", "SecretID");
return true;
}

59
handle.h Normal file
View File

@ -0,0 +1,59 @@
#pragma once
#include <curl/curl.h>
#include <string>
#include <openssl/evp.h>
#include <openssl/err.h>
class CHttpsHandle
{
public:
CHttpsHandle();
~CHttpsHandle();
public:
std::string sendGetRequest(const std::string& url);
private:
static size_t WriteCallback(void* contents, size_t size, size_t nmemb, void* userp);
private:
CURL* curl{};
};
class CUtil
{
public:
CUtil() = default;
~CUtil() = default;
public:
static std::string generateMD5(const std::string& input);
static std::string generateRandomNumStr();
static std::string urlEncode(const std::string& str);
};
using str_t = std::string;
class CTransTool
{
public:
CTransTool() = default;
~CTransTool() = default;
public:
void set_id(const str_t& id, const str_t& secret_key);
std::string combine(const str_t& words, const str_t& from, const str_t& to);
private:
std::string appid_{};
std::string secret_key_{};
};
struct ConfigInfo {
std::string baseUrl;
std::string appID;
std::string secretID;
};
class CConfig
{
public:
CConfig() = default;
~CConfig() = default;
public:
bool parse_config(ConfigInfo& config, const std::string& config_path = "");
};

104
main.cpp Normal file
View File

@ -0,0 +1,104 @@
#include "handle.h"
#include <fstream>
#include <iostream>
#include <memory>
#include <nlohmann/json.hpp>
#include <xlnt/xlnt.hpp>
#include <thread>
// #include <filesystem>
using json = nlohmann::json;
// namespace fs = std::filesystem;
struct TResult {
std::string source;
std::string ret;
};
bool parse_result(const std::string& str, std::string& out)
{
try {
json j = json::parse(str);
auto trans_result = j["trans_result"];
for (const auto& result : trans_result) {
out = result["dst"];
break;
}
return true;
} catch (const std::exception& e) {
std::cerr << "Error parsing JSON: " << e.what() << std::endl;
return false;
}
}
int main(int argc, char* argv[])
{
if (argc < 2) {
std::cout << "Second parm is file name(find in current director)." << std::endl;
return 0;
}
std::string file_name(argv[1]);
std::cout << "Will Parse:" << file_name << std::endl;
ConfigInfo base_info;
auto config = std::make_shared<CConfig>();
if (!config->parse_config(base_info, "fanyi.ini")) {
std::cerr << "Parse fanyi.ini failed, Please Check!" << std::endl;
return -1;
}
std::cout << "BaseURL:" << base_info.baseUrl << "\n";
std::cout << "AppID:" << base_info.appID << "\n";
std::cout << "SecretID:" << base_info.secretID << std::endl;
auto https = std::make_shared<CHttpsHandle>();
auto trans_tool = std::make_shared<CTransTool>();
trans_tool->set_id(base_info.appID, base_info.secretID);
auto trans = [&](const std::string& words, std::string& out) -> bool {
std::string request_url = base_info.baseUrl + trans_tool->combine(words, "auto", "en");
std::string response = https->sendGetRequest(request_url);
if (response.empty()) {
return false;
}
return parse_result(response, out);
};
// 读取文件
std::ifstream in(file_name);
if (!in.is_open()) {
std::cerr << "File Open Failed:" << file_name << std::endl;
return -1;
}
std::vector<TResult> vec;
std::string line;
while (std::getline(in, line)) {
if (line.empty()) {
continue;
}
std::string ret;
std::cout << "翻译：" << line << std::endl;
if (!trans(line, ret)) {
vec.emplace_back(TResult{line, "Failed"});
} else {
vec.emplace_back(TResult{line, ret});
}
std::this_thread::sleep_for(std::chrono::seconds(1));
}
in.close();
if (vec.empty()) {
std::cout << "vec is empty." << std::endl;
return -1;
}
xlnt::workbook wb;
xlnt::worksheet ws = wb.active_sheet();
int row = 1;
for (const auto& item : vec) {
ws.cell(1, row).value(item.source);
ws.cell(2, row).value(item.ret);
++row;
}
wb.save("out.xlsx");
return 0;
}