diff --git a/fsa/fsa.hpp b/fsa/fsa.hpp index 052f46a..09c1dc8 100644 --- a/fsa/fsa.hpp +++ b/fsa/fsa.hpp @@ -15,6 +15,7 @@ #include <exception> #include <string> #include <vector> +#include <netinet/in.h> template <class T> class State; template <class T> class FSA; @@ -83,6 +84,11 @@ public: */ static FSA<T>* getFSA(const unsigned char* ptr, const Deserializer<T>& deserializer); + /** + * Create an FSA object from file + */ + static FSA<T>* getFSA(const std::string& filename, const Deserializer<T>& deserializer); + protected: /** diff --git a/fsa/fsa_impl.hpp b/fsa/fsa_impl.hpp index 8974b9b..abd6cc6 100644 --- a/fsa/fsa_impl.hpp +++ b/fsa/fsa_impl.hpp @@ -13,6 +13,7 @@ #include <utility> #include <iostream> #include <vector> +#include <string> #include <netinet/in.h> #include "utils.hpp" #include "const.hpp" @@ -55,6 +56,11 @@ State<T> FSA<T>::getInitialState() const { } template <class T> +FSA<T>* FSA<T>::getFSA(const std::string& filename, const Deserializer<T>& deserializer) { + return getFSA(readFile(filename.c_str()), deserializer); +} + +template <class T> FSA<T>* FSA<T>::getFSA(const unsigned char* ptr, const Deserializer<T>& deserializer) { uint32_t magicNumber = ntohl(*((uint32_t*) ptr)); @@ -64,7 +70,7 @@ FSA<T>* FSA<T>::getFSA(const unsigned char* ptr, const Deserializer<T>& deserial uint8_t versionNum = *(ptr + VERSION_NUM_OFFSET); if (versionNum != VERSION_NUM) { - throw FSAException(string("Invalid version number: ") + to_string(versionNum) + ", should be: " + to_string(VERSION_NUM)); + throw FSAException(string("Invalid version number: ") + std::to_string(versionNum) + ", should be: " + to_string(VERSION_NUM)); } uint8_t implementationNum = *(ptr + IMPLEMENTATION_NUM_OFFSET); diff --git a/morfeusz/CMakeLists.txt b/morfeusz/CMakeLists.txt index 62d98bf..60f6ac9 100644 --- a/morfeusz/CMakeLists.txt +++ b/morfeusz/CMakeLists.txt @@ -7,9 +7,11 @@ include_directories (${Morfeusz_SOURCE_DIR}/fsa) add_library (morfeusz2 morfeusz.hpp morfeusz.cpp) add_executable (morfeusz2_analyze main.cpp) add_executable (test_morph test_morph.cpp MorphDeserializer.cpp Tagset.cpp ../fsa/const.cpp MorphInterpretation.cpp) +add_executable (test_morfeusz test_morph.cpp MorphDeserializer.cpp Tagset.cpp ../fsa/const.cpp MorphInterpretation.cpp Morfeusz.cpp) # Link the executable to the Hello library. target_link_libraries (morfeusz2_analyze morfeusz2) set_target_properties ( morfeusz2_analyze PROPERTIES COMPILE_FLAGS "-std=gnu++0x" ) set_target_properties ( test_morph PROPERTIES COMPILE_FLAGS "-std=gnu++0x -Wall -O2" ) +set_target_properties ( test_morfeusz PROPERTIES COMPILE_FLAGS "-std=gnu++0x -Wall -O2" ) \ No newline at end of file diff --git a/morfeusz/EncodedInterpretation.hpp b/morfeusz/EncodedInterpretation.hpp index a707278..4f2d18f 100644 --- a/morfeusz/EncodedInterpretation.hpp +++ b/morfeusz/EncodedInterpretation.hpp @@ -15,6 +15,9 @@ using namespace std; +/* + * Lemma in a compressed format (as in an automaton) + */ struct EncodedLemma { int suffixToCut; string suffixToAdd; diff --git a/morfeusz/Morfeusz.cpp b/morfeusz/Morfeusz.cpp index e2f810d..bedb63c 100644 --- a/morfeusz/Morfeusz.cpp +++ b/morfeusz/Morfeusz.cpp @@ -1,18 +1,47 @@ /* * File: Morfeusz.cpp - * Author: lennyn + * Author: mlenart * * Created on November 13, 2013, 5:21 PM */ +#include <string> +#include "utils.hpp" #include "Morfeusz.hpp" +#include "MorphDeserializer.hpp" +#include "encoding/CharsetConverter.hpp" -Morfeusz::Morfeusz() { +using namespace std; + +static FSA<vector<EncodedInterpretation>>* initializeFSA(const string& filename) { + static Deserializer<vector<EncodedInterpretation>>* deserializer + = new MorphDeserializer(); + return FSA<vector<EncodedInterpretation>>::getFSA(filename, *deserializer); +} + +static CharsetConverter* initializeCharsetConverter() { + static CharsetConverter* converter = new UTF8CharsetConverter(); + return converter; } -Morfeusz::Morfeusz(const Morfeusz& orig) { +Morfeusz::Morfeusz(const string& filename) +: fsa(initializeFSA(filename)), charsetConverter(initializeCharsetConverter()) { + } +//Morfeusz::Morfeusz(const Morfeusz& orig) { +//} + Morfeusz::~Morfeusz() { + delete &this->fsa; +} + +AnalyzeResult Morfeusz::analyze(const std::string& text) { + const char* textStart = text.c_str(); + const char* textEnd = text.c_str() + text.length(); + AnalyzeResult res = { + ResultsIterator(textStart, textEnd, *this), + ResultsIterator(textEnd, textEnd, *this)}; + return res; } diff --git a/morfeusz/Morfeusz.hpp b/morfeusz/Morfeusz.hpp index 0c39144..9b5768a 100644 --- a/morfeusz/Morfeusz.hpp +++ b/morfeusz/Morfeusz.hpp @@ -9,8 +9,11 @@ #define MORFEUSZ_HPP #include <string> +#include <vector> +#include "EncodedInterpretation.hpp" +#include "fsa.hpp" #include "MorphInterpretation.hpp" -//#include "interpretations.hpp" +#include "encoding/CharsetConverter.hpp" class Morfeusz; class AnalyzeResult; @@ -18,22 +21,21 @@ class ResultsIterator; class Morfeusz { public: - + explicit Morfeusz(const std::string& filename); + virtual ~Morfeusz(); +// Morfeusz(const Morfeusz& orig); AnalyzeResult analyze(const std::string& text); - Morfeusz(); - Morfeusz(const Morfeusz& orig); - virtual ~Morfeusz(); +// Morfeusz(); private: - void processOneWord(const char*& inputData, int startNodeNum, vector<MorphInterpretation>& resInterps); + void processOneWord(const char*& inputData, int startNodeNum, std::vector<MorphInterpretation>& resInterps); + const FSA<std::vector<EncodedInterpretation>>* fsa; + CharsetConverter* charsetConverter; }; class ResultsIterator { public: ResultsIterator( - const std::string& text, - const Morfeusz& morfeusz); - ResultsIterator( const char* startOfInput, const char* endOfInput, const Morfeusz& morfeusz); diff --git a/morfeusz/MorphInterpretation.cpp b/morfeusz/MorphInterpretation.cpp index b6aadc4..c6894c7 100644 --- a/morfeusz/MorphInterpretation.cpp +++ b/morfeusz/MorphInterpretation.cpp @@ -42,6 +42,14 @@ MorphInterpretation::MorphInterpretation( MorphInterpretation::~MorphInterpretation() { } +int MorphInterpretation::getStartNode() const { + return this->startNode; +} + +int MorphInterpretation::getEndNode() const { + return this->endNode; +} + const std::string& MorphInterpretation::getOrth() const { return this->orth; } diff --git a/morfeusz/MorphInterpretation.hpp b/morfeusz/MorphInterpretation.hpp index 683652d..bbebd28 100644 --- a/morfeusz/MorphInterpretation.hpp +++ b/morfeusz/MorphInterpretation.hpp @@ -21,6 +21,8 @@ public: const EncodedInterpretation& encodedInterp, const Tagset& tagset); virtual ~MorphInterpretation(); + int getStartNode() const; + int getEndNode() const; const std::string& getOrth() const; const std::string& getLemma() const; int getTagnum() const; diff --git a/morfeusz/encoding/CharsetConverter.cpp b/morfeusz/encoding/CharsetConverter.cpp new file mode 100644 index 0000000..358fb31 --- /dev/null +++ b/morfeusz/encoding/CharsetConverter.cpp @@ -0,0 +1,16 @@ +/* + * File: EncodingConverter.cpp + * Author: mlenart + * + * Created on 14 listopad 2013, 17:28 + */ + +#include "utf8.h" +#include "CharsetConverter.hpp" + +uint32_t UTF8CharsetConverter::next(const char*& it, const char* end) const { + return utf8::next(it, end); +} +const char* UTF8CharsetConverter::append(uint32_t cp, const char* result) const { + return utf8::append(cp, result); +} diff --git a/morfeusz/encoding/CharsetConverter.hpp b/morfeusz/encoding/CharsetConverter.hpp new file mode 100644 index 0000000..fa25f78 --- /dev/null +++ b/morfeusz/encoding/CharsetConverter.hpp @@ -0,0 +1,47 @@ +/* + * File: EncodingConverter.hpp + * Author: mlenart + * + * Created on 14 listopad 2013, 17:28 + */ + +#ifndef ENCODINGCONVERTER_HPP +#define ENCODINGCONVERTER_HPP + +class CharsetConverter { +public: + virtual uint32_t next(const char*& it, const char* end) const = 0; + virtual const char* append(uint32_t cp, const char* result) const = 0; +private: +}; + +class UTF8CharsetConverter: public CharsetConverter { +public: + uint32_t next(const char*& it, const char* end) const; + const char* append(uint32_t cp, const char* result) const; +private: +}; + +class UTF16CharsetConverter: public CharsetConverter { +public: + uint32_t next(const char*& it, const char* end) const; + const char* append(uint32_t cp, const char* result) const; +private: +}; + +class UTF32CharsetConverter: public CharsetConverter { +public: + uint32_t next(const char*& it, const char* end) const; + const char* append(uint32_t cp, const char* result) const; +private: +}; + +class ISO8859_2_CharsetConverter: public CharsetConverter { +public: + uint32_t next(const char*& it, const char* end) const; + const char* append(uint32_t cp, const char* result) const; +private: +}; + +#endif /* ENCODINGCONVERTER_HPP */ + diff --git a/morfeusz/encoding/utf8.h b/morfeusz/encoding/utf8.h new file mode 100644 index 0000000..4e44514 --- /dev/null +++ b/morfeusz/encoding/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/morfeusz/encoding/utf8/checked.h b/morfeusz/encoding/utf8/checked.h new file mode 100644 index 0000000..1331155 --- /dev/null +++ b/morfeusz/encoding/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 <stdexcept> + +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 <typename octet_iterator> + 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<uint8_t>(cp); + else if (cp < 0x800) { // two octets + *(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else if (cp < 0x10000) { // three octets + *(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else { // four octets + *(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0); + *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + return result; + } + + template <typename octet_iterator, typename output_iterator> + 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 <typename octet_iterator, typename output_iterator> + 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 <typename octet_iterator> + 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 <typename octet_iterator> + uint32_t peek_next(octet_iterator it, octet_iterator end) + { + return utf8::next(it, end); + } + + template <typename octet_iterator> + 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 <typename octet_iterator> + 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 <typename octet_iterator, typename distance_type> + 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 octet_iterator> + typename std::iterator_traits<octet_iterator>::difference_type + distance (octet_iterator first, octet_iterator last) + { + typename std::iterator_traits<octet_iterator>::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::next(first, last); + return dist; + } + + template <typename u16bit_iterator, typename octet_iterator> + 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<uint16_t>(trail_surrogate)); + } + else + throw invalid_utf16(static_cast<uint16_t>(cp)); + + } + // Lone trail surrogate + else if (utf8::internal::is_trail_surrogate(cp)) + throw invalid_utf16(static_cast<uint16_t>(cp)); + + result = utf8::append(cp, result); + } + return result; + } + + template <typename u16bit_iterator, typename octet_iterator> + 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<uint16_t>((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast<uint16_t>(cp); + } + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::append(*(start++), result); + + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + 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 <typename octet_iterator> + class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> { + 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/morfeusz/encoding/utf8/core.h b/morfeusz/encoding/utf8/core.h new file mode 100644 index 0000000..d237583 --- /dev/null +++ b/morfeusz/encoding/utf8/core.h @@ -0,0 +1,330 @@ +// 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 <iterator> +#include <cstdint> + +namespace utf8 +{ + // The typedefs for 8-bit, 16-bit and 32-bit unsigned integers + // You may need to change them to match your system. + // These typedefs have the same names as ones from cstdint, or boost/cstdint +// typedef unsigned char uint8_t; +// typedef unsigned short uint16_t; +// typedef unsigned int 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<typename octet_type> + inline uint8_t mask8(octet_type oc) + { + return static_cast<uint8_t>(0xff & oc); + } + template<typename u16_type> + inline uint16_t mask16(u16_type oc) + { + return static_cast<uint16_t>(0xffff & oc); + } + template<typename octet_type> + inline bool is_trail(octet_type oc) + { + return ((utf8::internal::mask8(oc) >> 6) == 0x2); + } + + template <typename u16> + inline bool is_lead_surrogate(u16 cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX); + } + + template <typename u16> + inline bool is_trail_surrogate(u16 cp) + { + return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + template <typename u16> + inline bool is_surrogate(u16 cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + template <typename u32> + inline bool is_code_point_valid(u32 cp) + { + return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp)); + } + + template <typename octet_iterator> + inline typename std::iterator_traits<octet_iterator>::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 <typename octet_difference_type> + 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 <typename octet_iterator> + 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 <typename octet_iterator> + 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 <typename octet_iterator> + 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 <typename octet_iterator> + 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 <typename octet_iterator> + 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 <typename octet_iterator> + 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<octet_iterator>::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 <typename octet_iterator> + 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 <typename octet_iterator> + 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 <typename octet_iterator> + inline bool is_valid(octet_iterator start, octet_iterator end) + { + return (utf8::find_invalid(start, end) == end); + } + + template <typename octet_iterator> + 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 <typename octet_iterator> + 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/morfeusz/encoding/utf8/unchecked.h b/morfeusz/encoding/utf8/unchecked.h new file mode 100644 index 0000000..cb24271 --- /dev/null +++ b/morfeusz/encoding/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 <typename octet_iterator> + octet_iterator append(uint32_t cp, octet_iterator result) + { + if (cp < 0x80) // one octet + *(result++) = static_cast<uint8_t>(cp); + else if (cp < 0x800) { // two octets + *(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else if (cp < 0x10000) { // three octets + *(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else { // four octets + *(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0); + *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f)| 0x80); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + return result; + } + + template <typename octet_iterator> + uint32_t next(octet_iterator& it) + { + uint32_t cp = utf8::internal::mask8(*it); + typename std::iterator_traits<octet_iterator>::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 <typename octet_iterator> + uint32_t peek_next(octet_iterator it) + { + return utf8::unchecked::next(it); + } + + template <typename octet_iterator> + 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 <typename octet_iterator> + inline uint32_t previous(octet_iterator& it) + { + return utf8::unchecked::prior(it); + } + + template <typename octet_iterator, typename distance_type> + void advance (octet_iterator& it, distance_type n) + { + for (distance_type i = 0; i < n; ++i) + utf8::unchecked::next(it); + } + + template <typename octet_iterator> + typename std::iterator_traits<octet_iterator>::difference_type + distance (octet_iterator first, octet_iterator last) + { + typename std::iterator_traits<octet_iterator>::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::unchecked::next(first); + return dist; + } + + template <typename u16bit_iterator, typename octet_iterator> + 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 <typename u16bit_iterator, typename octet_iterator> + 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<uint16_t>((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast<uint16_t>(cp); + } + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::unchecked::append(*(start++), result); + + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + 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 <typename octet_iterator> + class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> { + 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 + diff --git a/morfeusz/test_morfeusz.cpp b/morfeusz/test_morfeusz.cpp new file mode 100644 index 0000000..7877a03 --- /dev/null +++ b/morfeusz/test_morfeusz.cpp @@ -0,0 +1,50 @@ +/* + * File: test_morfeusz.cpp + * Author: mlenart + * + * Created on 14 listopad 2013, 15:50 + */ + +#include <cstdlib> +#include <cstdio> +#include <sstream> +#include <iostream> + +#include "Morfeusz.hpp" + +using namespace std; + +void debug(const MorphInterpretation& interp) { + fprintf(stderr, + "%d %d %s %s %s %s\n", + interp.getStartNode(), interp.getEndNode(), + interp.getOrth(), interp.getLemma(), + interp.getTag(), interp.getName()); +} + +void doTest( + const Morfeusz& morfeusz, + const string& inputFilename) { + ifstream ifs; + // ifs.exceptions(std::ifstream::failbit | std::ifstream::badbit); + ifs.open(inputFilename, ios::binary); + string line; + while (getline(ifs, line)) { + AnalyzeResult res(morfeusz.analyze(line)); + while (res.iterator != res.end) { + debug(*res); + res++; + } + } + validate(ifs.eof(), "Failed to read the input file to the end"); +} + +int main(int argc, char** argv) { + validate(argc == 3, "Must provide exactly two arguments - FSA filename, and input filename."); + string fsaFilename = argv[1]; + string inputFilename = argv[2]; + Morfeusz morfeusz(fsaFilename); + doTest(morfeusz, inputFilename); + return 0; +} + diff --git a/morfeusz/test_morph.cpp b/morfeusz/test_morph.cpp index deab1e1..7f66f39 100644 --- a/morfeusz/test_morph.cpp +++ b/morfeusz/test_morph.cpp @@ -17,21 +17,6 @@ using namespace std; -void debug(const string& key, const vector<EncodedInterpretation> value) { - cerr << key << endl; - for (EncodedInterpretation i: value) { - cerr << "suffix to cut: " << i.lemma.suffixToCut << endl; - cerr << "suffix to add: " << i.lemma.suffixToAdd << endl; - cerr << "tag: " << i.tag << endl; - cerr << "name: " << i.nameClassifier << endl; - } - cerr << "==================" << endl; -} - -//void debug(const string& key, const TaggedInterpretation& value) { -// cerr << key << '\t' << value.toString() << endl; -//} - void doTest( const FSA<vector<EncodedInterpretation>>& fsa, const Tagset& tagset, diff --git a/nbproject/configurations.xml b/nbproject/configurations.xml index 490b3f2..f4e3032 100644 --- a/nbproject/configurations.xml +++ b/nbproject/configurations.xml @@ -8,11 +8,13 @@ <in>test_speed.cpp</in> </df> <df root="morfeusz" name="1"> + <df name="encoding"> + <in>CharsetConverter.cpp</in> + <in>CharsetConverter.hpp</in> + </df> <in>Morfeusz.cpp</in> - <in>Morfeusz.hpp</in> <in>MorphDeserializer.cpp</in> <in>MorphInterpretation.cpp</in> - <in>MorphInterpretation.hpp</in> <in>Tagset.cpp</in> <in>main.cpp</in> <in>morfeusz.cpp</in> @@ -49,19 +51,11 @@ <executablePath>build/fsa/test_dict</executablePath> </makeTool> </makefileType> - <folder path="1"> + <item path="fsa/const.cpp" ex="false" tool="1" flavor2="4"> <ccTool> <incDir> <pElem>fsa</pElem> - <pElem>build/morfeusz</pElem> - </incDir> - </ccTool> - </folder> - <item path="fsa/const.cpp" ex="false" tool="1" flavor2="8"> - <ccTool> - <incDir> - <pElem>fsa</pElem> - <pElem>build/morfeusz</pElem> + <pElem>/usr/lib/gcc/x86_64-linux-gnu/4.8/include</pElem> </incDir> </ccTool> </item> @@ -86,32 +80,86 @@ </incDir> </ccTool> </item> - <item path="morfeusz/Morfeusz.cpp" ex="false" tool="1" flavor2="0"> - </item> - <item path="morfeusz/Morfeusz.hpp" ex="false" tool="3" flavor2="0"> + <item path="morfeusz/Morfeusz.cpp" ex="false" tool="1" flavor2="8"> + <ccTool> + <incDir> + <pElem>fsa</pElem> + <pElem>build/morfeusz</pElem> + </incDir> + </ccTool> </item> <item path="morfeusz/MorphDeserializer.cpp" ex="false" tool="1" flavor2="8"> <ccTool> + <incDir> + <pElem>fsa</pElem> + <pElem>build/morfeusz</pElem> + </incDir> </ccTool> </item> - <item path="morfeusz/MorphInterpretation.cpp" ex="false" tool="1" flavor2="0"> - </item> - <item path="morfeusz/MorphInterpretation.hpp" ex="false" tool="3" flavor2="0"> + <item path="morfeusz/MorphInterpretation.cpp" ex="false" tool="1" flavor2="4"> + <ccTool> + <incDir> + <pElem>morfeusz</pElem> + <pElem>/usr/include/c++/4.8/bits</pElem> + <pElem>/usr/include/c++/4.8/ext</pElem> + <pElem>/usr/include/c++/4.8</pElem> + <pElem>/usr/include/x86_64-linux-gnu/c++/4.8/bits</pElem> + <pElem>/usr/include/c++/4.8/debug</pElem> + <pElem>/usr/lib/gcc/x86_64-linux-gnu/4.8/include</pElem> + <pElem>/usr/include/c++/4.8/backward</pElem> + <pElem>/usr/include/x86_64-linux-gnu/c++/4.8</pElem> + <pElem>build/morfeusz</pElem> + </incDir> + </ccTool> </item> - <item path="morfeusz/Tagset.cpp" ex="false" tool="1" flavor2="8"> + <item path="morfeusz/Tagset.cpp" ex="false" tool="1" flavor2="4"> <ccTool> + <incDir> + <pElem>morfeusz</pElem> + <pElem>/usr/include/c++/4.8/bits</pElem> + <pElem>/usr/include/c++/4.8/ext</pElem> + <pElem>/usr/include/c++/4.8</pElem> + <pElem>/usr/include/x86_64-linux-gnu/c++/4.8/bits</pElem> + <pElem>/usr/include/c++/4.8/debug</pElem> + <pElem>/usr/lib/gcc/x86_64-linux-gnu/4.8/include</pElem> + <pElem>fsa</pElem> + <pElem>/usr/include/c++/4.8/backward</pElem> + <pElem>/usr/include/x86_64-linux-gnu/c++/4.8</pElem> + <pElem>build/morfeusz</pElem> + </incDir> </ccTool> </item> + <item path="morfeusz/encoding/CharsetConverter.cpp" + ex="false" + tool="1" + flavor2="0"> + </item> + <item path="morfeusz/encoding/CharsetConverter.hpp" + ex="false" + tool="3" + flavor2="0"> + </item> <item path="morfeusz/main.cpp" ex="false" tool="1" flavor2="8"> <ccTool> + <incDir> + <pElem>fsa</pElem> + <pElem>build/morfeusz</pElem> + </incDir> </ccTool> </item> <item path="morfeusz/morfeusz.cpp" ex="false" tool="1" flavor2="4"> <ccTool> + <incDir> + <pElem>morfeusz</pElem> + </incDir> </ccTool> </item> <item path="morfeusz/test_morph.cpp" ex="false" tool="1" flavor2="8"> <ccTool> + <incDir> + <pElem>fsa</pElem> + <pElem>build/morfeusz</pElem> + </incDir> </ccTool> </item> </conf> diff --git a/nbproject/project.xml b/nbproject/project.xml index 84b35e8..3e5e686 100644 --- a/nbproject/project.xml +++ b/nbproject/project.xml @@ -6,7 +6,7 @@ <name>morfeusz</name> <c-extensions/> <cpp-extensions>cpp</cpp-extensions> - <header-extensions>hpp</header-extensions> + <header-extensions>h,hpp</header-extensions> <sourceEncoding>UTF-8</sourceEncoding> <make-dep-projects/> <sourceRootList>