InterpretedChunksDecoder4Analyzer.cpp
5.44 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
/*
* File: InterpretedChunksDecoder4Analyzer.cpp
* Author: mlenart
*
* Created on 15 maj 2014, 15:28
*/
#include "InterpretedChunksDecoder4Analyzer.hpp"
#include <string>
using namespace std;
InterpretedChunksDecoder4Analyzer::InterpretedChunksDecoder4Analyzer(const Environment& env) : InterpretedChunksDecoder(env) {
}
void InterpretedChunksDecoder4Analyzer::decode(
unsigned int startNode,
unsigned int endNode,
const InterpretedChunk& interpretedChunk,
std::vector<MorphInterpretation>& out) const {
string orth;
string lemmaPrefix;
if (convertPrefixes(interpretedChunk, orth, lemmaPrefix)) {
// orth += this->env.getCharsetConverter().toString(interpretedChunk.originalCodepoints);
orth.insert(orth.end(), interpretedChunk.textStartPtr, interpretedChunk.textEndPtr);
const unsigned char* currPtr = interpretedChunk.interpsPtr;
while (currPtr < interpretedChunk.interpsEndPtr) {
this->decodeMorphInterpretation(startNode, endNode, orth, lemmaPrefix, interpretedChunk, false, currPtr, out);
}
}
}
void InterpretedChunksDecoder4Analyzer::decodeLemma(
const vector<uint32_t>& orth,
const EncodedForm& lemma,
bool forPrefix,
string& res) const {
for (unsigned int i = lemma.prefixToCut; i < orth.size() - lemma.suffixToCut; i++) {
uint32_t cp =
(i < lemma.casePattern.size() && lemma.casePattern[i])
? env.getCaseConverter().toTitle(orth[i])
: orth[i];
env.getCharsetConverter().append(cp, res);
}
if (!forPrefix) {
const char* suffixPtr = lemma.suffixToAdd.c_str();
const char* suffixEnd = suffixPtr + lemma.suffixToAdd.length();
while (suffixPtr != suffixEnd) {
uint32_t cp = UTF8CharsetConverter::getInstance().next(suffixPtr, suffixEnd);
env.getCharsetConverter().append(cp, res);
}
}
}
void InterpretedChunksDecoder4Analyzer::deserializeEncodedForm(const unsigned char*& ptr, unsigned char compressionByte, EncodedForm& encodedForm) const {
encodedForm.prefixToCut = hasCompressedPrefixCut(compressionByte)
? getPrefixCutLength(compressionByte)
: readInt8(ptr);
encodedForm.suffixToCut = readInt8(ptr);
encodedForm.suffixToAdd = readString(ptr);
assert(encodedForm.casePattern.size() == 0);
if (isLemmaOnlyLower(compressionByte)) {
// encodedForm.casePattern = std::vector<bool>();
}
else if (isLemmaOnlyTitle(compressionByte)) {
// encodedForm.casePattern = std::vector<bool>();
encodedForm.casePattern.push_back(true);
}
else {
encodedForm.casePattern = env.getCasePatternHelper().deserializeOneCasePattern(ptr);
}
}
EncodedInterpretation InterpretedChunksDecoder4Analyzer::deserializeEncodedInterp(const unsigned char*& ptr, unsigned char compressionByte) const {
EncodedInterpretation interp;
if (isOrthOnlyLower(compressionByte)) {
}
else if (isOrthOnlyTitle(compressionByte)) {
interp.orthCasePattern.push_back(true);
}
else {
interp.orthCasePattern = this->env.getCasePatternHelper().deserializeOneCasePattern(ptr);
}
deserializeEncodedForm(ptr, compressionByte, interp.value);
interp.tag = readInt16(ptr);
interp.nameClassifier = *ptr++;
interp.qualifiers = readInt16(ptr);
return interp;
}
void InterpretedChunksDecoder4Analyzer::decodeMorphInterpretation(
unsigned int startNode, unsigned int endNode,
const string& orth,
const string& lemmaPrefix,
const InterpretedChunk& chunk,
bool forPrefix,
const unsigned char*& ptr,
std::vector<MorphInterpretation>& out) const {
string lemma(lemmaPrefix);
orthCodepoints.clear();
normalizedCodepoints.clear();
const char* currPtr = chunk.textStartPtr;
while (currPtr != chunk.textEndPtr) {
uint32_t cp = env.getCharsetConverter().next(currPtr, chunk.textEndPtr);
orthCodepoints.push_back(cp);
normalizedCodepoints.push_back(env.getCaseConverter().toLower(cp));
}
EncodedInterpretation ei = this->deserializeEncodedInterp(ptr, *chunk.interpsGroupPtr);
if (env.getCasePatternHelper().checkCasePattern(normalizedCodepoints, orthCodepoints, ei.orthCasePattern)) {
this->decodeLemma(normalizedCodepoints, ei.value, forPrefix, lemma);
// pair<string, string> lemmaHomonymId = getLemmaHomonymIdPair(lemma);
out.push_back(MorphInterpretation(
startNode, endNode,
orth, lemma,
// "",
ei.tag,
ei.nameClassifier,
ei.qualifiers,
env));
}
}
bool InterpretedChunksDecoder4Analyzer::convertPrefixes(const InterpretedChunk& interpretedChunk, std::string& orth, std::string& lemmaPrefix) const {
for (unsigned int i = 0; i < interpretedChunk.prefixChunks.size(); i++) {
const InterpretedChunk& prefixChunk = interpretedChunk.prefixChunks[i];
orth.insert(orth.end(), prefixChunk.textStartPtr, prefixChunk.textEndPtr);
const unsigned char* ptr = prefixChunk.interpsPtr;
std::vector<MorphInterpretation> mi;
this->decodeMorphInterpretation(0, 0, orth, string(""), prefixChunk, true, ptr, mi);
if (!mi.empty()) {
lemmaPrefix += mi[0].getLemma();
}
else {
return false;
}
}
return true;
}