summaryrefslogtreecommitdiff
path: root/lib/parse_lng.h
blob: 19a8e7515b5be2c22460c69fe21e1a8d591b8aae (plain)
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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
// **************************************************************************
// * This file is part of the FreeFileSync project. It is distributed under *
// * GNU General Public License: http://www.gnu.org/licenses/gpl.html       *
// * Copyright (C) Zenju (zenju AT gmx DOT de) - All Rights Reserved        *
// **************************************************************************

#ifndef PARSE_LNG_HEADER_INCLUDED
#define PARSE_LNG_HEADER_INCLUDED

#include <algorithm>
#include <cctype>
#include <functional>
#include <memory>
#include <map>
#include <set>
#include <sstream>
#include <stdexcept>
#include <string>
#include <vector>
#include <list>
#include <zen/utf.h>
#include <zen/string_tools.h>
#include "parse_plural.h"
//#include <zen/perf.h>

namespace lngfile
{
//singular forms
typedef std::map <std::string, std::string> TranslationMap;  //orig |-> translation

//plural forms
typedef std::pair<std::string, std::string> SingularPluralPair; //1 house| n houses
typedef std::vector<std::string> PluralForms; //1 dom | 2 domy | 5 domów
typedef std::map<SingularPluralPair, PluralForms> TranslationPluralMap; //(sing/plu) |-> pluralforms

struct TransHeader
{
    TransHeader() : pluralCount(0) {}
    std::string languageName;     //display name: "English (UK)"
    std::string translatorName;   //"Zenju"
    std::string localeName;       //ISO 639 language code + ISO 3166 country code, e.g. "en_GB", or "en_US"
    std::string flagFile;         //"england.png"
    int pluralCount;              //2
    std::string pluralDefinition; //"n == 1 ? 0 : 1"
};


struct ParsingError
{
    ParsingError(const std::wstring& msg, size_t row, size_t col) : msg_(msg), row_(row), col_(col) {}
    std::wstring msg_; //parser error message
    size_t row_; //starting with 0
    size_t col_; //
};
void parseLng(const std::string& fileStream, TransHeader& header, TranslationMap& out, TranslationPluralMap& pluralOut); //throw ParsingError
void parseHeader(const std::string& fileStream, TransHeader& header); //throw ParsingError

class TranslationUnorderedList; //unordered list of unique translation items
std::string generateLng(const TranslationUnorderedList& in, const TransHeader& header);



















//--------------------------- implementation ---------------------------
enum class TranslationNewItemPos
{
    REL,
    TOP
};

class TranslationUnorderedList //unordered list of unique translation items
{
public:
    TranslationUnorderedList(TranslationNewItemPos newItemPos, TranslationMap&& transOld, TranslationPluralMap&& transPluralOld) :
        newItemPos_(newItemPos), transOld_(std::move(transOld)), transPluralOld_(std::move(transPluralOld)) {}

    void addItem(const std::string& orig)
    {
        if (!transUnique.insert(orig).second) return;
        auto it = transOld_.find(orig);
        if (it != transOld_.end() && !it->second.empty()) //preserve old translation from .lng file if existing
            sequence.push_back(std::make_shared<RegularItem>(std::make_pair(orig, it->second)));
        else
            switch (newItemPos_)
            {
                case TranslationNewItemPos::REL:
                    sequence.push_back(std::make_shared<RegularItem>(std::make_pair(orig, std::string())));
                    break;
                case TranslationNewItemPos::TOP:
                    sequence.push_front(std::make_shared<RegularItem>(std::make_pair(orig, std::string()))); //put untranslated items to the front of the .lng filebreak;
                    break;
            }
    }

    void addItem(const SingularPluralPair& orig)
    {
        if (!pluralUnique.insert(orig).second) return;
        auto it = transPluralOld_.find(orig);
        if (it != transPluralOld_.end() && !it->second.empty()) //preserve old translation from .lng file if existing
            sequence.push_back(std::make_shared<PluralItem>(std::make_pair(orig, it->second)));
        else
            switch (newItemPos_)
            {
                case TranslationNewItemPos::REL:
                    sequence.push_back(std::make_shared<PluralItem>(std::make_pair(orig, PluralForms())));
                    break;
                case TranslationNewItemPos::TOP:
                    sequence.push_front(std::make_shared<PluralItem>(std::make_pair(orig, PluralForms()))); //put untranslated items to the front of the .lng file
                    break;
            }
    }

    bool untranslatedTextExists() const { return std::any_of(sequence.begin(), sequence.end(), [](const std::shared_ptr<Item>& item) { return !item->hasTranslation(); }); }

    template <class Function, class Function2>
    void visitItems(Function onTrans, Function2 onPluralTrans) const //onTrans takes (const TranslationMap::value_type&), onPluralTrans takes (const TranslationPluralMap::value_type&)
    {
        for (const auto& item : sequence)
            if (auto regular = dynamic_cast<const RegularItem*>(item.get()))
                onTrans(regular->value);
            else if (auto plural = dynamic_cast<const PluralItem*>(item.get()))
                onPluralTrans(plural->value);
            else assert(false);
    }

private:
    struct Item { virtual ~Item() {} virtual bool hasTranslation() const = 0; };
    struct RegularItem : public Item { RegularItem(const TranslationMap      ::value_type& val) : value(val) {} virtual bool hasTranslation() const { return !value.second.empty(); } TranslationMap      ::value_type value; };
    struct PluralItem  : public Item { PluralItem (const TranslationPluralMap::value_type& val) : value(val) {} virtual bool hasTranslation() const { return !value.second.empty(); } TranslationPluralMap::value_type value; };

    const TranslationNewItemPos newItemPos_;
    std::list<std::shared_ptr<Item>> sequence; //ordered list of translation elements

    std::set<TranslationMap      ::key_type> transUnique;  //check uniqueness
    std::set<TranslationPluralMap::key_type> pluralUnique; //

    const TranslationMap transOld_;             //reuse existing translation
    const TranslationPluralMap transPluralOld_; //
};


struct Token
{
    enum Type
    {
        //header information
        TK_HEADER_BEGIN,
        TK_HEADER_END,
        TK_LANG_NAME_BEGIN,
        TK_LANG_NAME_END,
        TK_TRANS_NAME_BEGIN,
        TK_TRANS_NAME_END,
        TK_LOCALE_NAME_BEGIN,
        TK_LOCALE_NAME_END,
        TK_FLAG_FILE_BEGIN,
        TK_FLAG_FILE_END,
        TK_PLURAL_COUNT_BEGIN,
        TK_PLURAL_COUNT_END,
        TK_PLURAL_DEF_BEGIN,
        TK_PLURAL_DEF_END,

        //item level
        TK_SRC_BEGIN,
        TK_SRC_END,
        TK_TRG_BEGIN,
        TK_TRG_END,
        TK_TEXT,
        TK_PLURAL_BEGIN,
        TK_PLURAL_END,
        TK_END
    };

    Token(Type t) : type(t) {}
    Type type;

    std::string text;
};


class KnownTokens
{
public:
    typedef std::map<Token::Type, std::string> TokenMap;

    static const TokenMap& getList()
    {
        static KnownTokens inst;
        return inst.tokens;
    }

    static std::string text(Token::Type t)
    {
        auto it = getList().find(t);
        return it != getList().end() ? it->second : std::string();
    }

private:
    KnownTokens()
    {
        //header information
        tokens.insert(std::make_pair(Token::TK_HEADER_BEGIN,      "<header>"));
        tokens.insert(std::make_pair(Token::TK_HEADER_END,        "</header>"));
        tokens.insert(std::make_pair(Token::TK_LANG_NAME_BEGIN,   "<language>"));
        tokens.insert(std::make_pair(Token::TK_LANG_NAME_END,     "</language>"));
        tokens.insert(std::make_pair(Token::TK_TRANS_NAME_BEGIN,  "<translator>"));
        tokens.insert(std::make_pair(Token::TK_TRANS_NAME_END,    "</translator>"));
        tokens.insert(std::make_pair(Token::TK_LOCALE_NAME_BEGIN, "<locale>"));
        tokens.insert(std::make_pair(Token::TK_LOCALE_NAME_END,   "</locale>"));
        tokens.insert(std::make_pair(Token::TK_FLAG_FILE_BEGIN,   "<image>"));
        tokens.insert(std::make_pair(Token::TK_FLAG_FILE_END,     "</image>"));
        tokens.insert(std::make_pair(Token::TK_PLURAL_COUNT_BEGIN, "<plural_count>"));
        tokens.insert(std::make_pair(Token::TK_PLURAL_COUNT_END,   "</plural_count>"));
        tokens.insert(std::make_pair(Token::TK_PLURAL_DEF_BEGIN,  "<plural_definition>"));
        tokens.insert(std::make_pair(Token::TK_PLURAL_DEF_END,    "</plural_definition>"));

        //item level
        tokens.insert(std::make_pair(Token::TK_SRC_BEGIN,    "<source>"));
        tokens.insert(std::make_pair(Token::TK_SRC_END,      "</source>"));
        tokens.insert(std::make_pair(Token::TK_TRG_BEGIN,    "<target>"));
        tokens.insert(std::make_pair(Token::TK_TRG_END,      "</target>"));
        tokens.insert(std::make_pair(Token::TK_PLURAL_BEGIN, "<pluralform>"));
        tokens.insert(std::make_pair(Token::TK_PLURAL_END,   "</pluralform>"));
    }
    TokenMap tokens;
};


class Scanner
{
public:
    Scanner(const std::string& fileStream) : stream(fileStream), pos(stream.begin())
    {
        if (zen::startsWith(stream, zen::BYTE_ORDER_MARK_UTF8))
            pos += zen::strLength(zen::BYTE_ORDER_MARK_UTF8);
    }

    Token nextToken()
    {
        //skip whitespace
        pos = std::find_if(pos, stream.end(), [](char c) { return !zen::isWhiteSpace(c); });

        if (pos == stream.end())
            return Token(Token::TK_END);

        for (const auto& token : KnownTokens::getList())
            if (startsWith(token.second))
            {
                pos += token.second.size();
                return Token(token.first);
            }

        //rest must be "text"
        auto itBegin = pos;
        while (pos != stream.end() && !startsWithKnownTag())
            pos = std::find(pos + 1, stream.end(), '<');

        std::string text(itBegin, pos);

        normalize(text); //remove whitespace from end ect.

        if (text.empty() && pos == stream.end())
            return Token(Token::TK_END);

        Token out(Token::TK_TEXT);
        out.text = text;
        return out;
    }

    size_t posRow() const //current row beginning with 0
    {
        //count line endings
        const size_t crSum = std::count(stream.begin(), pos, '\r'); //carriage returns
        const size_t nlSum = std::count(stream.begin(), pos, '\n'); //new lines
        assert(crSum == 0 || nlSum == 0 || crSum == nlSum);
        return std::max(crSum, nlSum); //be compatible with Linux/Mac/Win
    }

    size_t posCol() const //current col beginning with 0
    {
        //seek beginning of line
        for (auto it = pos; it != stream.begin(); )
        {
            --it;
            if (*it == '\r' || *it == '\n')
                return pos - it - 1;
        }
        return pos - stream.begin();
    }

private:
    bool startsWithKnownTag() const
    {
        return std::any_of(KnownTokens::getList().begin(), KnownTokens::getList().end(),
        [&](const KnownTokens::TokenMap::value_type& p) { return startsWith(p.second); });
    }

    bool startsWith(const std::string& prefix) const
    {
        if (stream.end() - pos < static_cast<ptrdiff_t>(prefix.size()))
            return false;
        return std::equal(prefix.begin(), prefix.end(), pos);
    }

    static void normalize(std::string& text)
    {
        zen::trim(text); //remove whitespace from both ends

        //Delimiter:
        //----------
        //Linux: 0xA        \n
        //Mac:   0xD        \r
        //Win:   0xD 0xA    \r\n    <- language files are in Windows format
        zen::replace(text, "\r\n", '\n'); //
        zen::replace(text, "\r",   '\n'); //ensure c-style line breaks
    }

    const std::string stream;
    std::string::const_iterator pos;
};


class LngParser
{
public:
    LngParser(const std::string& fileStream) : scn(fileStream), tk(scn.nextToken()) {}

    void parse(TranslationMap& out, TranslationPluralMap& pluralOut, TransHeader& header)
    {
        parseHeader(header);

        try
        {
            parse_plural::PluralFormInfo pi(header.pluralDefinition, header.pluralCount);

            //items
            while (token().type != Token::TK_END)
                parseRegular(out, pluralOut, pi);
        }
        catch (const parse_plural::InvalidPluralForm&)
        {
            throw ParsingError(L"Invalid plural form definition", scn.posRow(), scn.posCol());
        }
    }

    void parseHeader(TransHeader& header)
    {
        consumeToken(Token::TK_HEADER_BEGIN);

        consumeToken(Token::TK_LANG_NAME_BEGIN);
        header.languageName = tk.text;
        consumeToken(Token::TK_TEXT);
        consumeToken(Token::TK_LANG_NAME_END);

        consumeToken(Token::TK_TRANS_NAME_BEGIN);
        header.translatorName = tk.text;
        consumeToken(Token::TK_TEXT);
        consumeToken(Token::TK_TRANS_NAME_END);

        consumeToken(Token::TK_LOCALE_NAME_BEGIN);
        header.localeName = tk.text;
        consumeToken(Token::TK_TEXT);
        consumeToken(Token::TK_LOCALE_NAME_END);

        consumeToken(Token::TK_FLAG_FILE_BEGIN);
        header.flagFile = tk.text;
        consumeToken(Token::TK_TEXT);
        consumeToken(Token::TK_FLAG_FILE_END);

        consumeToken(Token::TK_PLURAL_COUNT_BEGIN);
        header.pluralCount = zen::stringTo<int>(tk.text);
        consumeToken(Token::TK_TEXT);
        consumeToken(Token::TK_PLURAL_COUNT_END);

        consumeToken(Token::TK_PLURAL_DEF_BEGIN);
        header.pluralDefinition = tk.text;
        consumeToken(Token::TK_TEXT);
        consumeToken(Token::TK_PLURAL_DEF_END);

        consumeToken(Token::TK_HEADER_END);
    }

private:
    void parseRegular(TranslationMap& out, TranslationPluralMap& pluralOut, const parse_plural::PluralFormInfo& pluralInfo)
    {
        consumeToken(Token::TK_SRC_BEGIN);

        if (token().type == Token::TK_PLURAL_BEGIN)
            return parsePlural(pluralOut, pluralInfo);

        if (token().type != Token::TK_TEXT)
            throw ParsingError(L"Source text empty", scn.posRow(), scn.posCol());
        std::string original = tk.text;
        nextToken();

        consumeToken(Token::TK_SRC_END);

        consumeToken(Token::TK_TRG_BEGIN);
        std::string translation;
        if (token().type == Token::TK_TEXT)
        {
            translation = token().text;
            nextToken();
        }
        consumeToken(Token::TK_TRG_END);

        validateTranslation(original, translation); //throw throw ParsingError
        out.insert(std::make_pair(original, translation));
    }

    void parsePlural(TranslationPluralMap& pluralOut, const parse_plural::PluralFormInfo& pluralInfo)
    {
        //Token::TK_SRC_BEGIN already consumed

        consumeToken(Token::TK_PLURAL_BEGIN);
        std::string engSingular = tk.text;
        consumeToken(Token::TK_TEXT);
        consumeToken(Token::TK_PLURAL_END);

        consumeToken(Token::TK_PLURAL_BEGIN);
        std::string engPlural = tk.text;
        consumeToken(Token::TK_TEXT);
        consumeToken(Token::TK_PLURAL_END);

        consumeToken(Token::TK_SRC_END);

        consumeToken(Token::TK_TRG_BEGIN);

        PluralForms pluralList;
        while (token().type == Token::TK_PLURAL_BEGIN)
        {
            consumeToken(Token::TK_PLURAL_BEGIN);
            std::string pluralForm = tk.text;
            consumeToken(Token::TK_TEXT);
            consumeToken(Token::TK_PLURAL_END);
            pluralList.push_back(pluralForm);
        }

        consumeToken(Token::TK_TRG_END);

        const SingularPluralPair original(engSingular, engPlural);
        validateTranslation(original, pluralList, pluralInfo);
        pluralOut.insert(std::make_pair(original, pluralList));
    }

    void validateTranslation(const std::string& original, const std::string& translation) //throw ParsingError
    {
        if (original.empty())
            throw ParsingError(L"Source translation is empty", scn.posRow(), scn.posCol());

        if (!translation.empty())
        {
            //if original contains placeholder, so should translation!
            auto checkPlaceholder = [&](const std::string& placeholder)
            {
                if (zen::contains(original, placeholder) &&
                    !zen::contains(translation, placeholder))
                    throw ParsingError(zen::replaceCpy<std::wstring>(L"Placeholder %x missing in translation", L"%x", zen::utfCvrtTo<std::wstring>(placeholder)), scn.posRow(), scn.posCol());
            };
            checkPlaceholder("%x");
            checkPlaceholder("%y");
            checkPlaceholder("%z");

            //if source contains ampersand to mark menu accellerator key, so must translation
            if (hasSingleAmpersand(original) && !hasSingleAmpersand(translation))
                throw ParsingError(L"Translation is missing the & character to mark an access key for the menu item", scn.posRow(), scn.posCol());
        }
    }

    void validateTranslation(const SingularPluralPair& original, const PluralForms& translation, const parse_plural::PluralFormInfo& pluralInfo) //throw ParsingError
    {
        using namespace zen;
        //check the primary placeholder is existing at least for the second english text
        if (!contains(original.second, "%x"))
            throw ParsingError(L"Plural form source does not contain %x placeholder", scn.posRow(), scn.posCol());

        if (!translation.empty())
        {
            //check for invalid number of plural forms
            if (pluralInfo.getCount() != static_cast<int>(translation.size()))
                throw ParsingError(replaceCpy(replaceCpy<std::wstring>(L"Invalid number of plural forms; actual: %x, expected: %y", L"%x", numberTo<std::wstring>(translation.size())), L"%y", numberTo<std::wstring>(pluralInfo.getCount())), scn.posRow(), scn.posCol());

            //check for duplicate plural form translations (catch copy & paste errors for single-number form translations)
            for (auto it = translation.begin(); it != translation.end(); ++it)
                if (!contains(*it, "%x"))
                {
                    auto it2 = std::find(it + 1, translation.end(), *it);
                    if (it2 != translation.end())
                        throw ParsingError(replaceCpy<std::wstring>(L"Duplicate plural form translation at index position %x", L"%x", numberTo<std::wstring>(it2 - translation.begin())), scn.posRow(), scn.posCol());
                }

            for (int pos = 0; pos < static_cast<int>(translation.size()); ++pos)
                if (pluralInfo.isSingleNumberForm(pos))
                {
                    //translation needs to use decimal number if english source does so (e.g. frequently changing text like statistics)
                    if (contains(original.first, "%x") ||
                        contains(original.first, "1"))
                    {
                        const int firstNumber = pluralInfo.getFirstNumber(pos);
                        if (!(contains(translation[pos], "%x") ||
                              contains(translation[pos], numberTo<std::string>(firstNumber))))
                            throw ParsingError(replaceCpy<std::wstring>(replaceCpy<std::wstring>(L"Plural form translation at index position %y needs to use the decimal number %z or the %x placeholder",
                                                                                                 L"%y", numberTo<std::wstring>(pos)), L"%z", numberTo<std::wstring>(firstNumber)), scn.posRow(), scn.posCol());
                    }
                }
                else
                {
                    //ensure the placeholder is used when needed
                    if (!contains(translation[pos], "%x"))
                        throw ParsingError(replaceCpy<std::wstring>(L"Plural form at index position %y is missing the %x placeholder", L"%y", numberTo<std::wstring>(pos)), scn.posRow(), scn.posCol());
                }

            auto checkSecondaryPlaceholder = [&](const std::string& placeholder)
            {
                //make sure secondary placeholder is used in both source texts (or none)
                if (zen::contains(original.first,  placeholder) ||
                    zen::contains(original.second, placeholder))
                {
                    if (!zen::contains(original.first,  placeholder) ||
                        !zen::contains(original.second, placeholder))
                        throw ParsingError(zen::replaceCpy<std::wstring>(L"Placeholder %x missing in plural form source", L"%x", zen::utfCvrtTo<std::wstring>(placeholder)), scn.posRow(), scn.posCol());

                    //secondary placeholder is required for all plural forms
                    if (!std::all_of(translation.begin(), translation.end(), [&](const std::string& pform) { return zen::contains(pform, placeholder); }))
                    throw ParsingError(zen::replaceCpy<std::wstring>(L"Placeholder %x missing in plural form translation", L"%x", zen::utfCvrtTo<std::wstring>(placeholder)), scn.posRow(), scn.posCol());
                }
            };

            checkSecondaryPlaceholder("%y");
            checkSecondaryPlaceholder("%z");
        }
    }

    static bool hasSingleAmpersand(const std::string& str)
    {
        size_t pos = 0;
        for (;;)
        {
            pos = str.find('&', pos);
            if (pos == std::string::npos)
                return false;

            bool freeBefore = pos == 0 || str[pos - 1] != '&';
            bool freeAfter  = pos >= str.size() - 1 || str[pos + 1] != '&'; //str.size() > 0 here!

            if (freeBefore && freeAfter) //make sure to not catch && which windows resolves as just one & for display!
                return true;
            ++pos;
        }
    }

    void nextToken() { tk = scn.nextToken(); }
    const Token& token() const { return tk; }

    void consumeToken(Token::Type t) //throw ParsingError
    {
        expectToken(t); //throw ParsingError
        nextToken();
    }

    void expectToken(Token::Type t) //throw ParsingError
    {
        if (token().type != t)
            throw ParsingError(L"Unexpected token", scn.posRow(), scn.posCol());
    }

    Scanner scn;
    Token tk;
};


inline
void parseLng(const std::string& fileStream, TransHeader& header, TranslationMap& out, TranslationPluralMap& pluralOut) //throw ParsingError
{
    out.clear();
    pluralOut.clear();

    LngParser(fileStream).parse(out, pluralOut, header);
}


inline
void parseHeader(const std::string& fileStream, TransHeader& header) //throw ParsingError
{
    LngParser(fileStream).parseHeader(header);
}


inline
void formatMultiLineText(std::string& text)
{
    assert(!zen::contains(text, "\r\n"));

    if (text.find('\n') != std::string::npos) //multiple lines
    {
        if (*text.begin() != '\n')
            text = '\n' + text;
        if (*text.rbegin() != '\n')
            text += '\n';
    }
}


std::string generateLng(const TranslationUnorderedList& in, const TransHeader& header)
{
    std::string out;
    //header
    out += KnownTokens::text(Token::TK_HEADER_BEGIN) + '\n';

    out += '\t' + KnownTokens::text(Token::TK_LANG_NAME_BEGIN);
    out += header.languageName;
    out += KnownTokens::text(Token::TK_LANG_NAME_END) + '\n';

    out += '\t' + KnownTokens::text(Token::TK_TRANS_NAME_BEGIN);
    out += header.translatorName;
    out += KnownTokens::text(Token::TK_TRANS_NAME_END) + '\n';

    out += '\t' + KnownTokens::text(Token::TK_LOCALE_NAME_BEGIN);
    out += header.localeName;
    out += KnownTokens::text(Token::TK_LOCALE_NAME_END) + '\n';

    out += '\t' + KnownTokens::text(Token::TK_FLAG_FILE_BEGIN);
    out += header.flagFile;
    out += KnownTokens::text(Token::TK_FLAG_FILE_END) + '\n';

    out += '\t' + KnownTokens::text(Token::TK_PLURAL_COUNT_BEGIN);
    out += zen::numberTo<std::string>(header.pluralCount);
    out += KnownTokens::text(Token::TK_PLURAL_COUNT_END) + '\n';

    out += '\t' + KnownTokens::text(Token::TK_PLURAL_DEF_BEGIN);
    out += header.pluralDefinition;
    out += KnownTokens::text(Token::TK_PLURAL_DEF_END) + '\n';

    out += KnownTokens::text(Token::TK_HEADER_END) + '\n';

    out += '\n';


    in.visitItems([&](const TranslationMap::value_type& trans)
    {
        std::string original    = trans.first;
        std::string translation = trans.second;

        formatMultiLineText(original);
        formatMultiLineText(translation);

        out += KnownTokens::text(Token::TK_SRC_BEGIN);
        out += original;
        out += KnownTokens::text(Token::TK_SRC_END) + '\n';

        out += KnownTokens::text(Token::TK_TRG_BEGIN);
        out += translation;
        out += KnownTokens::text(Token::TK_TRG_END) + '\n' + '\n';
    },
    [&](const TranslationPluralMap::value_type& transPlural)
    {
        std::string engSingular  = transPlural.first.first;
        std::string engPlural    = transPlural.first.second;
        const PluralForms& forms = transPlural.second;

        formatMultiLineText(engSingular);
        formatMultiLineText(engPlural);

        out += KnownTokens::text(Token::TK_SRC_BEGIN) + '\n';
        out += KnownTokens::text(Token::TK_PLURAL_BEGIN);
        out += engSingular;
        out += KnownTokens::text(Token::TK_PLURAL_END) + '\n';
        out += KnownTokens::text(Token::TK_PLURAL_BEGIN);
        out += engPlural;
        out += KnownTokens::text(Token::TK_PLURAL_END) + '\n';
        out += KnownTokens::text(Token::TK_SRC_END) + '\n';

        out += KnownTokens::text(Token::TK_TRG_BEGIN);
        out += '\n';

        for (std::string plForm : forms)
        {
            formatMultiLineText(plForm);

            out += KnownTokens::text(Token::TK_PLURAL_BEGIN);
            out += plForm;
            out += KnownTokens::text(Token::TK_PLURAL_END) + '\n';
        }
        out += KnownTokens::text(Token::TK_TRG_END) + '\n' + '\n';
    });

    assert(!zen::contains(out, "\r\n") && !zen::contains(out, "\r"));
    return zen::replaceCpy(out, '\n', "\r\n"); //back to win line endings
}
}

#endif //PARSE_LNG_HEADER_INCLUDED
bgstack15