From aa4d426b4d3527d7e166df1a05058c9a4a0f6683 Mon Sep 17 00:00:00 2001 From: Wojtek Kosior Date: Fri, 30 Apr 2021 00:33:56 +0200 Subject: initial/final commit --- vmime-master/contrib/punycode/punycode.c | 264 +++++++++++++++++++++++ vmime-master/contrib/punycode/punycode.h | 84 ++++++++ vmime-master/contrib/utf8/utf8.h | 34 +++ vmime-master/contrib/utf8/utf8/checked.h | 327 +++++++++++++++++++++++++++++ vmime-master/contrib/utf8/utf8/core.h | 326 ++++++++++++++++++++++++++++ vmime-master/contrib/utf8/utf8/unchecked.h | 228 ++++++++++++++++++++ 6 files changed, 1263 insertions(+) create mode 100644 vmime-master/contrib/punycode/punycode.c create mode 100644 vmime-master/contrib/punycode/punycode.h create mode 100644 vmime-master/contrib/utf8/utf8.h create mode 100644 vmime-master/contrib/utf8/utf8/checked.h create mode 100644 vmime-master/contrib/utf8/utf8/core.h create mode 100644 vmime-master/contrib/utf8/utf8/unchecked.h (limited to 'vmime-master/contrib') diff --git a/vmime-master/contrib/punycode/punycode.c b/vmime-master/contrib/punycode/punycode.c new file mode 100644 index 0000000..f669aa0 --- /dev/null +++ b/vmime-master/contrib/punycode/punycode.c @@ -0,0 +1,264 @@ +/* +punycode.c from RFC 3492 +http://www.nicemice.net/idn/ +Adam M. Costello +http://www.nicemice.net/amc/ + +This is ANSI C code (C89) implementing Punycode (RFC 3492). + +*/ + +#include + +/*** Bootstring parameters for Punycode ***/ + +enum { base = 36, tmin = 1, tmax = 26, skew = 38, damp = 700, + initial_bias = 72, initial_n = 0x80, delimiter = 0x2D }; + +/* basic(cp) tests whether cp is a basic code point: */ +#define basic(cp) ((punycode_uint)(cp) < 0x80) + +/* delim(cp) tests whether cp is a delimiter: */ +#define delim(cp) ((cp) == delimiter) + +/* decode_digit(cp) returns the numeric value of a basic code */ +/* point (for use in representing integers) in the range 0 to */ +/* base-1, or base if cp is does not represent a value. */ + +static punycode_uint decode_digit(punycode_uint cp) +{ + return cp - 48 < 10 ? cp - 22 : cp - 65 < 26 ? cp - 65 : + cp - 97 < 26 ? cp - 97 : (punycode_uint) base; +} + +/* encode_digit(d,flag) returns the basic code point whose value */ +/* (when used for representing integers) is d, which needs to be in */ +/* the range 0 to base-1. The lowercase form is used unless flag is */ +/* nonzero, in which case the uppercase form is used. The behavior */ +/* is undefined if flag is nonzero and digit d has no uppercase form. */ + +static char encode_digit(punycode_uint d, int flag) +{ + return char(d + 22 + 75 * (d < 26) - ((flag != 0) << 5)); + /* 0..25 map to ASCII a..z or A..Z */ + /* 26..35 map to ASCII 0..9 */ +} + +/* flagged(bcp) tests whether a basic code point is flagged */ +/* (uppercase). The behavior is undefined if bcp is not a */ +/* basic code point. */ + +#define flagged(bcp) ((punycode_uint)(bcp) - 65 < 26) + +/* encode_basic(bcp,flag) forces a basic code point to lowercase */ +/* if flag is zero, uppercase if flag is nonzero, and returns */ +/* the resulting code point. The code point is unchanged if it */ +/* is caseless. The behavior is undefined if bcp is not a basic */ +/* code point. */ + +static char encode_basic(punycode_uint bcp, int flag) +{ + bcp -= (bcp - 97 < 26) << 5; + return char(bcp + ((!flag && (bcp - 65 < 26)) << 5)); +} + +/*** Platform-specific constants ***/ + +/* maxint is the maximum value of a punycode_uint variable: */ +static const punycode_uint maxint = -1U; +/* Because maxint is unsigned, -1 becomes the maximum value. */ + +/*** Bias adaptation function ***/ + +static punycode_uint adapt( + punycode_uint delta, punycode_uint numpoints, int firsttime ) +{ + punycode_uint k; + + delta = firsttime ? delta / damp : delta >> 1; + /* delta >> 1 is a faster way of doing delta / 2 */ + delta += delta / numpoints; + + for (k = 0; delta > ((base - tmin) * tmax) / 2; k += base) { + delta /= base - tmin; + } + + return k + (base - tmin + 1) * delta / (delta + skew); +} + +/*** Main encode function ***/ + +enum punycode_status punycode_encode( + punycode_uint input_length, + const punycode_uint input[], + const unsigned char case_flags[], + punycode_uint *output_length, + char output[] ) +{ + punycode_uint n, delta, h, b, out, max_out, bias, j, m, q, k, t; + + /* Initialize the state: */ + + n = initial_n; + delta = out = 0; + max_out = *output_length; + bias = initial_bias; + + /* Handle the basic code points: */ + + for (j = 0; j < input_length; ++j) { + if (basic(input[j])) { + if (max_out - out < 2) return punycode_big_output; + output[out++] = char( + case_flags ? encode_basic(input[j], case_flags[j]) : input[j] + ); + } + /* else if (input[j] < n) return punycode_bad_input; */ + /* (not needed for Punycode with unsigned code points) */ + } + + h = b = out; + + /* h is the number of code points that have been handled, b is the */ + /* number of basic code points, and out is the number of characters */ + /* that have been output. */ + + if (b > 0) output[out++] = delimiter; + + /* Main encoding loop: */ + + while (h < input_length) { + /* All non-basic code points < n have been */ + /* handled already. Find the next larger one: */ + + for (m = maxint, j = 0; j < input_length; ++j) { + /* if (basic(input[j])) continue; */ + /* (not needed for Punycode) */ + if (input[j] >= n && input[j] < m) m = input[j]; + } + + /* Increase delta enough to advance the decoder's */ + /* state to , but guard against overflow: */ + + if (m - n > (maxint - delta) / (h + 1)) return punycode_overflow; + delta += (m - n) * (h + 1); + n = m; + + for (j = 0; j < input_length; ++j) { + /* Punycode does not need to check whether input[j] is basic: */ + if (input[j] < n /* || basic(input[j]) */ ) { + if (++delta == 0) return punycode_overflow; + } + + if (input[j] == n) { + /* Represent delta as a generalized variable-length integer: */ + + for (q = delta, k = base; ; k += base) { + if (out >= max_out) return punycode_big_output; + t = k <= bias /* + tmin */ ? (punycode_uint) tmin : /* +tmin not needed */ + k >= (punycode_uint) bias + (punycode_uint) tmax ? (punycode_uint) tmax : k - (punycode_uint) bias; + if (q < t) break; + output[out++] = encode_digit(t + (q - t) % (base - t), 0); + q = (q - t) / (base - t); + } + + output[out++] = encode_digit(q, case_flags && case_flags[j]); + bias = adapt(delta, h + 1, h == b); + delta = 0; + ++h; + } + } + + ++delta, ++n; + } + + *output_length = out; + return punycode_success; +} + +/*** Main decode function ***/ + +enum punycode_status punycode_decode( + punycode_uint input_length, + const char input[], + punycode_uint *output_length, + punycode_uint output[], + unsigned char case_flags[] ) +{ + punycode_uint n, out, i, max_out, bias, + b, j, in, oldi, w, k, digit, t; + + /* Initialize the state: */ + + n = initial_n; + out = i = 0; + max_out = *output_length; + bias = initial_bias; + + /* Handle the basic code points: Let b be the number of input code */ + /* points before the last delimiter, or 0 if there is none, then */ + /* copy the first b code points to the output. */ + + for (b = j = 0; j < input_length; ++j) if (delim(input[j])) b = j; + if (b > max_out) return punycode_big_output; + + for (j = 0; j < b; ++j) { + if (case_flags) case_flags[out] = flagged(input[j]); + if (!basic(input[j])) return punycode_bad_input; + output[out++] = input[j]; + } + + /* Main decoding loop: Start just after the last delimiter if any */ + /* basic code points were copied; start at the beginning otherwise. */ + + for (in = b > 0 ? b + 1 : 0; in < input_length; ++out) { + + /* in is the index of the next character to be consumed, and */ + /* out is the number of code points in the output array. */ + + /* Decode a generalized variable-length integer into delta, */ + /* which gets added to i. The overflow checking is easier */ + /* if we increase i as we go, then subtract off its starting */ + /* value at the end to obtain delta. */ + + for (oldi = i, w = 1, k = base; ; k += base) { + if (in >= input_length) return punycode_bad_input; + digit = decode_digit(input[in++]); + if (digit >= base) return punycode_bad_input; + if (digit > (maxint - i) / w) return punycode_overflow; + i += digit * w; + t = k <= (punycode_uint) bias /* + tmin */ ? (punycode_uint) tmin : /* +tmin not needed */ + k >= (punycode_uint) bias + (punycode_uint) tmax ? (punycode_uint) tmax : k - (punycode_uint) bias; + if (digit < t) break; + if (w > maxint / (base - t)) return punycode_overflow; + w *= (base - t); + } + + bias = adapt(i - oldi, out + 1, oldi == 0); + + /* i was supposed to wrap around from out+1 to 0, */ + /* incrementing n each time, so we'll fix that now: */ + + if (i / (out + 1) > maxint - n) return punycode_overflow; + n += i / (out + 1); + i %= (out + 1); + + /* Insert n at position i of the output: */ + + /* not needed for Punycode: */ + /* if (decode_digit(n) <= base) return punycode_invalid_input; */ + if (out >= max_out) return punycode_big_output; + + if (case_flags) { + memmove(case_flags + i + 1, case_flags + i, out - i); + /* Case of last character determines uppercase flag: */ + case_flags[i] = flagged(input[in - 1]); + } + + memmove(output + i + 1, output + i, (out - i) * sizeof *output); + output[i++] = n; + } + + *output_length = out; + return punycode_success; +} diff --git a/vmime-master/contrib/punycode/punycode.h b/vmime-master/contrib/punycode/punycode.h new file mode 100644 index 0000000..fb02ee9 --- /dev/null +++ b/vmime-master/contrib/punycode/punycode.h @@ -0,0 +1,84 @@ +/* +punycode.h from RFC 3492 +http://www.nicemice.net/idn/ +Adam M. Costello +http://www.nicemice.net/amc/ + +This is ANSI C code (C89) implementing Punycode (RFC 3492). + +*/ + +#include + +enum punycode_status { + punycode_success, + punycode_bad_input, /* Input is invalid. */ + punycode_big_output, /* Output would exceed the space provided. */ + punycode_overflow /* Input needs wider integers to process. */ +}; + +#if UINT_MAX >= (1 << 26) - 1 +typedef unsigned int punycode_uint; +#else +typedef unsigned long punycode_uint; +#endif + +enum punycode_status punycode_encode( + punycode_uint input_length, + const punycode_uint input[], + const unsigned char case_flags[], + punycode_uint *output_length, + char output[] ); + + /* punycode_encode() converts Unicode to Punycode. The input */ + /* is represented as an array of Unicode code points (not code */ + /* units; surrogate pairs are not allowed), and the output */ + /* will be represented as an array of ASCII code points. The */ + /* output string is *not* null-terminated; it will contain */ + /* zeros if and only if the input contains zeros. (Of course */ + /* the caller can leave room for a terminator and add one if */ + /* needed.) The input_length is the number of code points in */ + /* the input. The output_length is an in/out argument: the */ + /* caller passes in the maximum number of code points that it */ + /* can receive, and on successful return it will contain the */ + /* number of code points actually output. The case_flags array */ + /* holds input_length boolean values, where nonzero suggests that */ + /* the corresponding Unicode character be forced to uppercase */ + /* after being decoded (if possible), and zero suggests that */ + /* it be forced to lowercase (if possible). ASCII code points */ + /* are encoded literally, except that ASCII letters are forced */ + /* to uppercase or lowercase according to the corresponding */ + /* uppercase flags. If case_flags is a null pointer then ASCII */ + /* letters are left as they are, and other code points are */ + /* treated as if their uppercase flags were zero. The return */ + /* value can be any of the punycode_status values defined above */ + /* except punycode_bad_input; if not punycode_success, then */ + /* output_size and output might contain garbage. */ + +enum punycode_status punycode_decode( + punycode_uint input_length, + const char input[], + punycode_uint *output_length, + punycode_uint output[], + unsigned char case_flags[] ); + + /* punycode_decode() converts Punycode to Unicode. The input is */ + /* represented as an array of ASCII code points, and the output */ + /* will be represented as an array of Unicode code points. The */ + /* input_length is the number of code points in the input. The */ + /* output_length is an in/out argument: the caller passes in */ + /* the maximum number of code points that it can receive, and */ + /* on successful return it will contain the actual number of */ + /* code points output. The case_flags array needs room for at */ + /* least output_length values, or it can be a null pointer if the */ + /* case information is not needed. A nonzero flag suggests that */ + /* the corresponding Unicode character be forced to uppercase */ + /* by the caller (if possible), while zero suggests that it be */ + /* forced to lowercase (if possible). ASCII code points are */ + /* output already in the proper case, but their flags will be set */ + /* appropriately so that applying the flags would be harmless. */ + /* The return value can be any of the punycode_status values */ + /* defined above; if not punycode_success, then output_length, */ + /* output, and case_flags might contain garbage. On success, the */ + /* decoder will never need to write an output_length greater than */ + /* input_length, because of how the encoding is defined. */ diff --git a/vmime-master/contrib/utf8/utf8.h b/vmime-master/contrib/utf8/utf8.h new file mode 100644 index 0000000..4e44514 --- /dev/null +++ b/vmime-master/contrib/utf8/utf8.h @@ -0,0 +1,34 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "utf8/checked.h" +#include "utf8/unchecked.h" + +#endif // header guard diff --git a/vmime-master/contrib/utf8/utf8/checked.h b/vmime-master/contrib/utf8/utf8/checked.h new file mode 100644 index 0000000..1331155 --- /dev/null +++ b/vmime-master/contrib/utf8/utf8/checked.h @@ -0,0 +1,327 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "core.h" +#include + +namespace utf8 +{ + // Base for the exceptions that may be thrown from the library + class exception : public ::std::exception { + }; + + // Exceptions that may be thrown from the library functions. + class invalid_code_point : public exception { + uint32_t cp; + public: + invalid_code_point(uint32_t cp) : cp(cp) {} + virtual const char* what() const throw() { return "Invalid code point"; } + uint32_t code_point() const {return cp;} + }; + + class invalid_utf8 : public exception { + uint8_t u8; + public: + invalid_utf8 (uint8_t u) : u8(u) {} + virtual const char* what() const throw() { return "Invalid UTF-8"; } + uint8_t utf8_octet() const {return u8;} + }; + + class invalid_utf16 : public exception { + uint16_t u16; + public: + invalid_utf16 (uint16_t u) : u16(u) {} + virtual const char* what() const throw() { return "Invalid UTF-16"; } + uint16_t utf16_word() const {return u16;} + }; + + class not_enough_room : public exception { + public: + virtual const char* what() const throw() { return "Not enough space"; } + }; + + /// The library API - functions intended to be called by the users + + template + octet_iterator append(uint32_t cp, octet_iterator result) + { + if (!utf8::internal::is_code_point_valid(cp)) + throw invalid_code_point(cp); + + if (cp < 0x80) // one octet + *(result++) = static_cast(cp); + else if (cp < 0x800) { // two octets + *(result++) = static_cast((cp >> 6) | 0xc0); + *(result++) = static_cast((cp & 0x3f) | 0x80); + } + else if (cp < 0x10000) { // three octets + *(result++) = static_cast((cp >> 12) | 0xe0); + *(result++) = static_cast(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast((cp & 0x3f) | 0x80); + } + else { // four octets + *(result++) = static_cast((cp >> 18) | 0xf0); + *(result++) = static_cast(((cp >> 12) & 0x3f) | 0x80); + *(result++) = static_cast(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast((cp & 0x3f) | 0x80); + } + return result; + } + + template + output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement) + { + while (start != end) { + octet_iterator sequence_start = start; + internal::utf_error err_code = utf8::internal::validate_next(start, end); + switch (err_code) { + case internal::UTF8_OK : + for (octet_iterator it = sequence_start; it != start; ++it) + *out++ = *it; + break; + case internal::NOT_ENOUGH_ROOM: + throw not_enough_room(); + case internal::INVALID_LEAD: + out = utf8::append (replacement, out); + ++start; + break; + case internal::INCOMPLETE_SEQUENCE: + case internal::OVERLONG_SEQUENCE: + case internal::INVALID_CODE_POINT: + out = utf8::append (replacement, out); + ++start; + // just one replacement mark for the sequence + while (start != end && utf8::internal::is_trail(*start)) + ++start; + break; + } + } + return out; + } + + template + inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out) + { + static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd); + return utf8::replace_invalid(start, end, out, replacement_marker); + } + + template + uint32_t next(octet_iterator& it, octet_iterator end) + { + uint32_t cp = 0; + internal::utf_error err_code = utf8::internal::validate_next(it, end, cp); + switch (err_code) { + case internal::UTF8_OK : + break; + case internal::NOT_ENOUGH_ROOM : + throw not_enough_room(); + case internal::INVALID_LEAD : + case internal::INCOMPLETE_SEQUENCE : + case internal::OVERLONG_SEQUENCE : + throw invalid_utf8(*it); + case internal::INVALID_CODE_POINT : + throw invalid_code_point(cp); + } + return cp; + } + + template + uint32_t peek_next(octet_iterator it, octet_iterator end) + { + return utf8::next(it, end); + } + + template + uint32_t prior(octet_iterator& it, octet_iterator start) + { + // can't do much if it == start + if (it == start) + throw not_enough_room(); + + octet_iterator end = it; + // Go back until we hit either a lead octet or start + while (utf8::internal::is_trail(*(--it))) + if (it == start) + throw invalid_utf8(*it); // error - no lead byte in the sequence + return utf8::peek_next(it, end); + } + + /// Deprecated in versions that include "prior" + template + uint32_t previous(octet_iterator& it, octet_iterator pass_start) + { + octet_iterator end = it; + while (utf8::internal::is_trail(*(--it))) + if (it == pass_start) + throw invalid_utf8(*it); // error - no lead byte in the sequence + octet_iterator temp = it; + return utf8::next(temp, end); + } + + template + void advance (octet_iterator& it, distance_type n, octet_iterator end) + { + for (distance_type i = 0; i < n; ++i) + utf8::next(it, end); + } + + template + typename std::iterator_traits::difference_type + distance (octet_iterator first, octet_iterator last) + { + typename std::iterator_traits::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::next(first, last); + return dist; + } + + template + octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) + { + while (start != end) { + uint32_t cp = utf8::internal::mask16(*start++); + // Take care of surrogate pairs first + if (utf8::internal::is_lead_surrogate(cp)) { + if (start != end) { + uint32_t trail_surrogate = utf8::internal::mask16(*start++); + if (utf8::internal::is_trail_surrogate(trail_surrogate)) + cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; + else + throw invalid_utf16(static_cast(trail_surrogate)); + } + else + throw invalid_utf16(static_cast(cp)); + + } + // Lone trail surrogate + else if (utf8::internal::is_trail_surrogate(cp)) + throw invalid_utf16(static_cast(cp)); + + result = utf8::append(cp, result); + } + return result; + } + + template + u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) + { + while (start != end) { + uint32_t cp = utf8::next(start, end); + if (cp > 0xffff) { //make a surrogate pair + *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast(cp); + } + return result; + } + + template + octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::append(*(start++), result); + + return result; + } + + template + u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) + { + while (start != end) + (*result++) = utf8::next(start, end); + + return result; + } + + // The iterator class + template + class iterator : public std::iterator { + octet_iterator it; + octet_iterator range_start; + octet_iterator range_end; + public: + iterator () {} + explicit iterator (const octet_iterator& octet_it, + const octet_iterator& range_start, + const octet_iterator& range_end) : + it(octet_it), range_start(range_start), range_end(range_end) + { + if (it < range_start || it > range_end) + throw std::out_of_range("Invalid utf-8 iterator position"); + } + // the default "big three" are OK + octet_iterator base () const { return it; } + uint32_t operator * () const + { + octet_iterator temp = it; + return utf8::next(temp, range_end); + } + bool operator == (const iterator& rhs) const + { + if (range_start != rhs.range_start || range_end != rhs.range_end) + throw std::logic_error("Comparing utf-8 iterators defined with different ranges"); + return (it == rhs.it); + } + bool operator != (const iterator& rhs) const + { + return !(operator == (rhs)); + } + iterator& operator ++ () + { + utf8::next(it, range_end); + return *this; + } + iterator operator ++ (int) + { + iterator temp = *this; + utf8::next(it, range_end); + return temp; + } + iterator& operator -- () + { + utf8::prior(it, range_start); + return *this; + } + iterator operator -- (int) + { + iterator temp = *this; + utf8::prior(it, range_start); + return temp; + } + }; // class iterator + +} // namespace utf8 + +#endif //header guard + + diff --git a/vmime-master/contrib/utf8/utf8/core.h b/vmime-master/contrib/utf8/utf8/core.h new file mode 100644 index 0000000..f858c4a --- /dev/null +++ b/vmime-master/contrib/utf8/utf8/core.h @@ -0,0 +1,326 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include + +namespace utf8 +{ + typedef vmime_uint8 uint8_t; + typedef vmime_uint16 uint16_t; + typedef vmime_uint32 uint32_t; + +// Helper code - not intended to be directly called by the library users. May be changed at any time +namespace internal +{ + // Unicode constants + // Leading (high) surrogates: 0xd800 - 0xdbff + // Trailing (low) surrogates: 0xdc00 - 0xdfff + const uint16_t LEAD_SURROGATE_MIN = 0xd800u; + const uint16_t LEAD_SURROGATE_MAX = 0xdbffu; + const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u; + const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu; + const uint16_t LEAD_OFFSET = LEAD_SURROGATE_MIN - (0x10000 >> 10); + const uint32_t SURROGATE_OFFSET = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN; + + // Maximum valid value for a Unicode code point + const uint32_t CODE_POINT_MAX = 0x0010ffffu; + + template + inline uint8_t mask8(octet_type oc) + { + return static_cast(0xff & oc); + } + template + inline uint16_t mask16(u16_type oc) + { + return static_cast(0xffff & oc); + } + template + inline bool is_trail(octet_type oc) + { + return ((utf8::internal::mask8(oc) >> 6) == 0x2); + } + + template + inline bool is_lead_surrogate(u16 cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX); + } + + template + inline bool is_trail_surrogate(u16 cp) + { + return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + template + inline bool is_surrogate(u16 cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + template + inline bool is_code_point_valid(u32 cp) + { + return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp)); + } + + template + inline typename std::iterator_traits::difference_type + sequence_length(octet_iterator lead_it) + { + uint8_t lead = utf8::internal::mask8(*lead_it); + if (lead < 0x80) + return 1; + else if ((lead >> 5) == 0x6) + return 2; + else if ((lead >> 4) == 0xe) + return 3; + else if ((lead >> 3) == 0x1e) + return 4; + else + return 0; + } + + template + inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length) + { + if (cp < 0x80) { + if (length != 1) + return true; + } + else if (cp < 0x800) { + if (length != 2) + return true; + } + else if (cp < 0x10000) { + if (length != 3) + return true; + } + + return false; + } + + enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT}; + + /// Helper for get_sequence_x + template + utf_error increase_safely(octet_iterator& it, octet_iterator end) + { + if (++it == end) + return NOT_ENOUGH_ROOM; + + if (!utf8::internal::is_trail(*it)) + return INCOMPLETE_SEQUENCE; + + return UTF8_OK; + } + + #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;} + + /// get_sequence_x functions decode utf-8 sequences of the length x + template + utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + return UTF8_OK; + } + + template + utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f); + + return UTF8_OK; + } + + template + utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; + } + + template + utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (utf8::internal::mask8(*it) << 6) & 0xfff; + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; + } + + #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR + + template + utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + // Save the original value of it so we can go back in case of failure + // Of course, it does not make much sense with i.e. stream iterators + octet_iterator original_it = it; + + uint32_t cp = 0; + // Determine the sequence length based on the lead octet + typedef typename std::iterator_traits::difference_type octet_difference_type; + const octet_difference_type length = utf8::internal::sequence_length(it); + + // Get trail octets and calculate the code point + utf_error err = UTF8_OK; + switch (length) { + case 0: + return INVALID_LEAD; + case 1: + err = utf8::internal::get_sequence_1(it, end, cp); + break; + case 2: + err = utf8::internal::get_sequence_2(it, end, cp); + break; + case 3: + err = utf8::internal::get_sequence_3(it, end, cp); + break; + case 4: + err = utf8::internal::get_sequence_4(it, end, cp); + break; + } + + if (err == UTF8_OK) { + // Decoding succeeded. Now, security checks... + if (utf8::internal::is_code_point_valid(cp)) { + if (!utf8::internal::is_overlong_sequence(cp, length)){ + // Passed! Return here. + code_point = cp; + ++it; + return UTF8_OK; + } + else + err = OVERLONG_SEQUENCE; + } + else + err = INVALID_CODE_POINT; + } + + // Failure branch - restore the original value of the iterator + it = original_it; + return err; + } + + template + inline utf_error validate_next(octet_iterator& it, octet_iterator end) { + uint32_t ignored; + return utf8::internal::validate_next(it, end, ignored); + } + +} // namespace internal + + /// The library API - functions intended to be called by the users + + // Byte order mark + const uint8_t bom[] = {0xef, 0xbb, 0xbf}; + + template + octet_iterator find_invalid(octet_iterator start, octet_iterator end) + { + octet_iterator result = start; + while (result != end) { + utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end); + if (err_code != internal::UTF8_OK) + return result; + } + return result; + } + + template + inline bool is_valid(octet_iterator start, octet_iterator end) + { + return (utf8::find_invalid(start, end) == end); + } + + template + inline bool starts_with_bom (octet_iterator it, octet_iterator end) + { + return ( + ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) && + ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) && + ((it != end) && (utf8::internal::mask8(*it)) == bom[2]) + ); + } + + //Deprecated in release 2.3 + template + inline bool is_bom (octet_iterator it) + { + return ( + (utf8::internal::mask8(*it++)) == bom[0] && + (utf8::internal::mask8(*it++)) == bom[1] && + (utf8::internal::mask8(*it)) == bom[2] + ); + } +} // namespace utf8 + +#endif // header guard + + diff --git a/vmime-master/contrib/utf8/utf8/unchecked.h b/vmime-master/contrib/utf8/utf8/unchecked.h new file mode 100644 index 0000000..cb24271 --- /dev/null +++ b/vmime-master/contrib/utf8/utf8/unchecked.h @@ -0,0 +1,228 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "core.h" + +namespace utf8 +{ + namespace unchecked + { + template + octet_iterator append(uint32_t cp, octet_iterator result) + { + if (cp < 0x80) // one octet + *(result++) = static_cast(cp); + else if (cp < 0x800) { // two octets + *(result++) = static_cast((cp >> 6) | 0xc0); + *(result++) = static_cast((cp & 0x3f) | 0x80); + } + else if (cp < 0x10000) { // three octets + *(result++) = static_cast((cp >> 12) | 0xe0); + *(result++) = static_cast(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast((cp & 0x3f) | 0x80); + } + else { // four octets + *(result++) = static_cast((cp >> 18) | 0xf0); + *(result++) = static_cast(((cp >> 12) & 0x3f)| 0x80); + *(result++) = static_cast(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast((cp & 0x3f) | 0x80); + } + return result; + } + + template + uint32_t next(octet_iterator& it) + { + uint32_t cp = utf8::internal::mask8(*it); + typename std::iterator_traits::difference_type length = utf8::internal::sequence_length(it); + switch (length) { + case 1: + break; + case 2: + it++; + cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f); + break; + case 3: + ++it; + cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); + ++it; + cp += (*it) & 0x3f; + break; + case 4: + ++it; + cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); + ++it; + cp += (utf8::internal::mask8(*it) << 6) & 0xfff; + ++it; + cp += (*it) & 0x3f; + break; + } + ++it; + return cp; + } + + template + uint32_t peek_next(octet_iterator it) + { + return utf8::unchecked::next(it); + } + + template + uint32_t prior(octet_iterator& it) + { + while (utf8::internal::is_trail(*(--it))) ; + octet_iterator temp = it; + return utf8::unchecked::next(temp); + } + + // Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous) + template + inline uint32_t previous(octet_iterator& it) + { + return utf8::unchecked::prior(it); + } + + template + void advance (octet_iterator& it, distance_type n) + { + for (distance_type i = 0; i < n; ++i) + utf8::unchecked::next(it); + } + + template + typename std::iterator_traits::difference_type + distance (octet_iterator first, octet_iterator last) + { + typename std::iterator_traits::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::unchecked::next(first); + return dist; + } + + template + octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) + { + while (start != end) { + uint32_t cp = utf8::internal::mask16(*start++); + // Take care of surrogate pairs first + if (utf8::internal::is_lead_surrogate(cp)) { + uint32_t trail_surrogate = utf8::internal::mask16(*start++); + cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; + } + result = utf8::unchecked::append(cp, result); + } + return result; + } + + template + u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) + { + while (start < end) { + uint32_t cp = utf8::unchecked::next(start); + if (cp > 0xffff) { //make a surrogate pair + *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast(cp); + } + return result; + } + + template + octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::unchecked::append(*(start++), result); + + return result; + } + + template + u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) + { + while (start < end) + (*result++) = utf8::unchecked::next(start); + + return result; + } + + // The iterator class + template + class iterator : public std::iterator { + octet_iterator it; + public: + iterator () {} + explicit iterator (const octet_iterator& octet_it): it(octet_it) {} + // the default "big three" are OK + octet_iterator base () const { return it; } + uint32_t operator * () const + { + octet_iterator temp = it; + return utf8::unchecked::next(temp); + } + bool operator == (const iterator& rhs) const + { + return (it == rhs.it); + } + bool operator != (const iterator& rhs) const + { + return !(operator == (rhs)); + } + iterator& operator ++ () + { + ::std::advance(it, utf8::internal::sequence_length(it)); + return *this; + } + iterator operator ++ (int) + { + iterator temp = *this; + ::std::advance(it, utf8::internal::sequence_length(it)); + return temp; + } + iterator& operator -- () + { + utf8::unchecked::prior(it); + return *this; + } + iterator operator -- (int) + { + iterator temp = *this; + utf8::unchecked::prior(it); + return temp; + } + }; // class iterator + + } // namespace utf8::unchecked +} // namespace utf8 + + +#endif // header guard + -- cgit v1.2.3