MUSX Document Model
Loading...
Searching...
No Matches
EnigmaString.h
1/*
2 * Copyright (C) 2025, Robert Patterson
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a copy
5 * of this software and associated documentation files (the "Software"), to deal
6 * in the Software without restriction, including without limitation the rights
7 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
8 * copies of the Software, and to permit persons to whom the Software is
9 * furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice shall be included in
12 * all copies or substantial portions of the Software.
13 *
14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
17 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
18 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
19 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
20 * THE SOFTWARE.
21 */
22#pragma once
23
24#include <cassert>
25#include <string>
26#include <string_view>
27#include <vector>
28#include <functional>
29#include <memory>
30#include <unordered_set>
31
32#include "musx/dom/Fundamentals.h"
33#include "musx/dom/MusxInstance.h"
34
35namespace musx {
36
37namespace dom {
38class FontInfo;
39class Document;
40class TextsBase;
41
42namespace options {
44}
45
46} // namespace dom
47
48namespace util {
49
53{
61 {
62 None,
63 MusicFont,
64 TextFont,
66 };
67
69 EnigmaStyles(const std::weak_ptr<dom::Document>& document)
70 : font(std::make_shared<dom::FontInfo>(document))
71 {
72 }
73
74 std::shared_ptr<dom::FontInfo> font;
78 int tracking{};
79};
80
81class EnigmaParsingContext;
82
148{
149public:
151 template <typename CharT>
152 static std::string fromU8(const CharT* s)
153 {
154 static_assert(std::is_same<CharT, char>::value || std::is_same<CharT, decltype(u8'a')>::value,
155 "fromU8() only accepts char or char8_t pointers");
156 return std::string(reinterpret_cast<const char*>(s));
157 }
158
160 static std::string toU8(char32_t cp);
161
168 {
175
183 };
184
191 {
203 Ascii,
204
216 Unicode,
217
229 Smufl
230 };
231
284
286 static bool startsWithFontCommand(const std::string& text);
287
289 static bool startsWithStyleCommand(const std::string& text);
290
292 static std::optional<dom::options::AccidentalInsertSymbolType> commandIsAccidentalType(std::string_view commandText);
293
314 static std::vector<std::string> parseComponents(const std::string& input, size_t* parsedLength = nullptr);
315
320 using TextChunkCallback = std::function<bool(
321 const std::string& text,
322 const EnigmaStyles& styles
323 )>;
324
334 using TextInsertCallback = std::function<std::optional<std::string>(
335 const std::vector<std::string>& parsedCommand
336 )>;
337
339 static inline TextInsertCallback defaultInsertsCallback = [](const std::vector<std::string>&) { return std::nullopt; };
340
366 static bool parseEnigmaText(const std::shared_ptr<dom::Document>& document, dom::Cmper forPartId, const std::string& rawText,
367 const TextChunkCallback& onText, const TextInsertCallback& onInsert,
368 const EnigmaParsingOptions& options = {}, const EnigmaParsingContext* parsingContext = nullptr)
369 {
370 return parseEnigmaTextImpl(document, forPartId, rawText, onText, onInsert, options, parsingContext, EnigmaStyles(document));
371 }
372
382 static bool parseEnigmaText(const std::shared_ptr<dom::Document>& document, dom::Cmper forPartId, const std::string& rawText, const TextChunkCallback& onText,
383 const EnigmaParsingOptions& options = {}, const EnigmaParsingContext* parsingContext = nullptr)
384 {
385 return parseEnigmaTextImpl(document, forPartId, rawText, onText, defaultInsertsCallback, options, parsingContext, EnigmaStyles(document));
386 }
387
396 static bool parseStyleCommand(std::vector<std::string> components, EnigmaStyles& styles);
397
399 static std::string trimTags(const std::string& input);
400
401private:
402 static bool parseEnigmaTextImpl(const std::shared_ptr<dom::Document>& document, dom::Cmper forPartId, const std::string& rawText,
403 const TextChunkCallback& onText, const TextInsertCallback& onInsert,
404 const EnigmaParsingOptions& options, const EnigmaParsingContext* parsingContext,
405 const EnigmaStyles& startingStyles);
406};
407
415{
416private:
418 dom::Cmper m_forPartId;
419 std::optional<int> m_forPageNumber;
421
422public:
425 : m_rawText(nullptr), m_forPartId(dom::SCORE_PARTID), m_insertFunc(EnigmaString::defaultInsertsCallback)
426 {}
427
434 std::optional<dom::Cmper> forPageId = std::nullopt,
436 : m_rawText(std::move(rawText)), m_forPartId(forPartId), m_forPageNumber(forPageId), m_insertFunc(insertFunc)
437 {}
438
440 explicit operator bool() const noexcept
441 { return static_cast<bool>(m_rawText); }
442
443 std::string affixText;
445
451 std::string getText(bool trimTags = false,
453 const std::unordered_set<std::string_view>& ignoreTags = {}) const;
454
462 const EnigmaString::TextInsertCallback& onInsert,
463 const EnigmaString::EnigmaParsingOptions& options = {}) const;
464
470 const EnigmaString::EnigmaParsingOptions& options = {}) const
471 {
473 }
474
480
482 dom::MusxInstance<dom::TextsBase> getRawText() const { return m_rawText; }
483
484 // If there is ever a need for a non-const version of the pointer, we can always
485 // look it up again.
486
488 dom::Cmper getRequestedPartId() const { return m_forPartId; }
489
491 std::optional<int> getPageNumber() const { return m_forPageNumber; }
492};
493
494} // namespace util
495} // namespace musx
Wrapper class for interpreting and rendering Enigma-style strings with insert handling.
Definition EnigmaString.h:415
bool affixIsPrefix
True if affixText is a prefix; false if it is a suffix.
Definition EnigmaString.h:444
std::string getText(bool trimTags=false, EnigmaString::AccidentalStyle accidentalStyle=EnigmaString::AccidentalStyle::Ascii, const std::unordered_set< std::string_view > &ignoreTags={}) const
Return displayable text with Enigma tags converted.
Definition EnigmaString.cpp:537
dom::MusxInstance< dom::FontInfo > parseFirstFontInfo() const
Returns a shared pointer to a FontInfo instance that reflects the first font information in the text.
Definition EnigmaString.cpp:551
bool parseEnigmaText(const EnigmaString::TextChunkCallback &onText, const EnigmaString::EnigmaParsingOptions &options={}) const
Parse the Enigma text into structured chunks with insert handling.
Definition EnigmaString.h:469
dom::Cmper getRequestedPartId() const
Get the requested part id.
Definition EnigmaString.h:488
std::optional< int > getPageNumber() const
Get the page number that was supplied, if any.
Definition EnigmaString.h:491
dom::MusxInstance< dom::TextsBase > getRawText() const
Get the raw text pointer.
Definition EnigmaString.h:482
EnigmaParsingContext(dom::MusxInstance< dom::TextsBase > rawText, dom::Cmper forPartId, std::optional< dom::Cmper > forPageId=std::nullopt, EnigmaString::TextInsertCallback insertFunc=EnigmaString::defaultInsertsCallback)
Constructor.
Definition EnigmaString.h:433
bool parseEnigmaText(const EnigmaString::TextChunkCallback &onText, const EnigmaString::TextInsertCallback &onInsert, const EnigmaString::EnigmaParsingOptions &options={}) const
Parse the Enigma text into structured chunks with insert handling.
Definition EnigmaString.cpp:514
EnigmaParsingContext()
Null constructor.
Definition EnigmaString.h:424
std::string affixText
Prefix or suffix to be passed in parsing options.
Definition EnigmaString.h:443
Static class that provides utilities to extract information from enigma strings. Enigma strings use t...
Definition EnigmaString.h:148
static std::string trimTags(const std::string &input)
Trims all enigma tags from an enigma string, leaving just the plain text.
Definition EnigmaString.cpp:479
static std::string fromU8(const CharT *s)
Convert u8"" literals to std::string in a way that works both in C++17 and C++20+.
Definition EnigmaString.h:152
static std::optional< dom::options::AccidentalInsertSymbolType > commandIsAccidentalType(std::string_view commandText)
Returns the accidental insert symbol type if the input command is an accidental insert.
Definition EnigmaString.cpp:203
static bool startsWithStyleCommand(const std::string &text)
Returns true if the enigma string starts with a style insert.
Definition EnigmaString.cpp:71
static bool parseStyleCommand(std::vector< std::string > components, EnigmaStyles &styles)
Incorporates an enigma font insert into the supplied dom::FontInfo instance.
Definition EnigmaString.cpp:149
static bool startsWithFontCommand(const std::string &text)
Returns true if the enigma string starts with a font insert.
Definition EnigmaString.cpp:59
AccidentalStyle
Enumeration to specify the type of accidental substitution representation.
Definition EnigmaString.h:191
@ Smufl
Use SMuFL notation-specific accidentals.
@ Ascii
Use ASCII substitutions for accidentals.
@ Unicode
Use Unicode text accidentals.
static std::string toU8(char32_t cp)
Concerts a 32-bit codepoint to a utf8-encoded std::string.
Definition EnigmaString.cpp:34
static bool parseEnigmaText(const std::shared_ptr< dom::Document > &document, dom::Cmper forPartId, const std::string &rawText, const TextChunkCallback &onText, const TextInsertCallback &onInsert, const EnigmaParsingOptions &options={}, const EnigmaParsingContext *parsingContext=nullptr)
Parses an Enigma-formatted string, handling font inserts and escaped carets.
Definition EnigmaString.h:366
static TextInsertCallback defaultInsertsCallback
Inserts callback to take all default insert subsitutions determined by parseEnigmaText.
Definition EnigmaString.h:339
AccidentalInsertHandling
Enumeration to specify the default handling for accidental insert commands. Like all Enigma commands,...
Definition EnigmaString.h:168
@ ParseToGlyphs
Parse accidental insert commands into glyph font changes and character strings.
@ Substitute
Substitute accidental insert commands with textual representations.
std::function< bool(const std::string &text, const EnigmaStyles &styles)> TextChunkCallback
Iteration function type that the parser calls back when the font has changed or when recursively pars...
Definition EnigmaString.h:323
static bool parseEnigmaText(const std::shared_ptr< dom::Document > &document, dom::Cmper forPartId, const std::string &rawText, const TextChunkCallback &onText, const EnigmaParsingOptions &options={}, const EnigmaParsingContext *parsingContext=nullptr)
Simplified version of parseEnigmaText that strips unhandled inserts. Useful in particular when the ca...
Definition EnigmaString.h:382
static std::vector< std::string > parseComponents(const std::string &input, size_t *parsedLength=nullptr)
Parses an enigma text insert into its constituent components.
Definition EnigmaString.cpp:85
std::function< std::optional< std::string >(const std::vector< std::string > &parsedCommand)> TextInsertCallback
Iteration function type that the parser calls back when it encounters an Enigma text insert that requ...
Definition EnigmaString.h:336
AccidentalInsertSymbolType
Insert symbol types for accidentals.
Definition Options.h:1465
std::shared_ptr< const T > MusxInstance
Defines the type of a musx instance stored in a pool.
Definition MusxInstance.h:35
int32_t Evpu
EVPU value (288 per inch)
Definition Fundamentals.h:57
uint16_t Cmper
Enigma "comperator" key type.
Definition Fundamentals.h:55
object model for musx file (enigmaxml)
Definition BaseClasses.h:36
Options for configuring how Enigma strings are parsed.
Definition EnigmaString.h:239
bool ignoreStyleTags
If value is true, font & style tags are ignored. Note that you may still get get font and style chang...
Definition EnigmaString.h:275
EnigmaParsingOptions()
constructor
Definition EnigmaString.h:241
EnigmaParsingOptions(AccidentalStyle accidentalStyle)
constructor for accidental substitution
Definition EnigmaString.h:246
AccidentalStyle substitutionStyle
Specifies the accidental substitution style used when insertHandling is Substitute.
Definition EnigmaString.h:264
std::unordered_set< std::string_view > ignoreTags
Skip tags in this set. Primarily used by the "partname" insert to avoid a situation where the partnam...
Definition EnigmaString.h:282
AccidentalInsertHandling insertHandling
Specifies how accidental insert commands are handled during parsing.
Definition EnigmaString.h:256
bool stripUnknownTags
Specifies whether to strip unknown tags or dump them into the output string.
Definition EnigmaString.h:269
Text styles for enigma strings.
Definition EnigmaString.h:53
EnigmaStyles(const std::weak_ptr< dom::Document > &document)
constructor
Definition EnigmaString.h:69
std::shared_ptr< dom::FontInfo > font
the font to use
Definition EnigmaString.h:74
CategoryTracking
Specifies is the current enigma style tracks an expressions marking category font....
Definition EnigmaString.h:61
@ NumberFont
tracks the category's number font (not implemented in Finale U.I.)
@ TextFont
tracks the category's text font
@ MusicFont
tracks the category's music font
int tracking
inter-character tracking in EMs (1/1000 font size)
Definition EnigmaString.h:78
dom::Evpu superscript
superscript setting added to baseline (positive means up)
Definition EnigmaString.h:77
dom::Evpu baseline
baseline setting (positive means up)
Definition EnigmaString.h:76
CategoryTracking categoryFont
how this font is tracked against a marking category
Definition EnigmaString.h:75