diff options
Diffstat (limited to 'src/tui/text.cc')
| -rw-r--r-- | src/tui/text.cc | 138 |
1 files changed, 138 insertions, 0 deletions
diff --git a/src/tui/text.cc b/src/tui/text.cc new file mode 100644 index 0000000..14f0e09 --- /dev/null +++ b/src/tui/text.cc @@ -0,0 +1,138 @@ +/* + * Ricochet - A minimalist CLI web browser for fast, distraction-free navigation. + * Copyright (C) 2026 Richard Qin + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <https://www.gnu.org/licenses/>. + */ + +#include "text.hh" + +#include <climits> +#include <cwchar> +#include <memory> +#include <stdexcept> +#include <unicode/ubrk.h> +#include <unicode/uchar.h> +#include <unicode/utext.h> +#include <utility> + +namespace ricochet::tui::detail { +namespace { + +using UnicodeText = std::unique_ptr<UText, decltype( &utext_close )>; +using Breaks = std::unique_ptr<UBreakIterator, decltype( &ubrk_close )>; + +Breaks breaks_for( UBreakIteratorType type, UText& text ) +{ + UErrorCode status = U_ZERO_ERROR; + Breaks breaks( ubrk_open( type, "root", nullptr, 0, &status ), &ubrk_close ); + if ( U_FAILURE( status ) ) { + throw std::runtime_error( u_errorName( status ) ); + } + ubrk_setUText( breaks.get(), &text, &status ); + if ( U_FAILURE( status ) ) { + throw std::runtime_error( u_errorName( status ) ); + } + return breaks; +} + +WordKind word_kind( UChar32 codepoint ) +{ + if ( u_isUWhiteSpace( codepoint ) ) { + return WordKind::Space; + } + if ( u_hasBinaryProperty( codepoint, UCHAR_IDEOGRAPHIC ) ) { + return WordKind::Ideograph; + } + if ( codepoint == '_' || u_isalnum( codepoint ) ) { + return WordKind::Word; + } + return WordKind::Punctuation; +} + +} // namespace + +TextService::TextService( std::size_t glyph_capacity ) : glyph_capacity_( glyph_capacity ) {} + +TextAnalysis TextService::analyze( std::string_view utf8, bool line_breaks, bool tabs ) const +{ + // ICU BreakIterator exposes int32_t native offsets even with a UTF-8 UText. + if ( utf8.size() > INT32_MAX ) { + throw std::length_error( "Text exceeds ICU break-iterator offset capacity" ); + } + UErrorCode status = U_ZERO_ERROR; + UnicodeText text( + utext_openUTF8( nullptr, utf8.empty() ? "" : utf8.data(), static_cast<int64_t>( utf8.size() ), &status ), + &utext_close ); + if ( U_FAILURE( status ) ) { + throw std::runtime_error( u_errorName( status ) ); + } + auto characters = breaks_for( UBRK_CHARACTER, *text ); + auto lines = breaks_for( UBRK_LINE, *text ); + TextAnalysis result; + int32_t begin = ubrk_first( characters.get() ); + int32_t line_end = ubrk_next( lines.get() ); + WordKind previous = WordKind::Space; + for ( int32_t end = ubrk_next( characters.get() ); end != UBRK_DONE; + begin = end, end = ubrk_next( characters.get() ) ) { + while ( line_end != UBRK_DONE && line_end < end ) { + line_end = ubrk_next( lines.get() ); + } + Grapheme glyph { .bytes = { static_cast<std::size_t>( begin ), static_cast<std::size_t>( end ) }, + .break_after = line_end == end }; + utext_setNativeIndex( text.get(), begin ); + const auto first = utext_next32( text.get() ); + glyph.word = word_kind( first ); + const auto source = utf8.substr( glyph.bytes.start, glyph.bytes.end - glyph.bytes.start ); + if ( line_breaks && ( source == "\n" || source == "\r\n" ) ) { + glyph.kind = TextUnitKind::LineBreak; + glyph.columns = 0; + } else if ( tabs && source == "\t" ) { + glyph.kind = TextUnitKind::Tab; + glyph.display = L" "; + } else { + const int width = ::wcwidth( static_cast<wchar_t>( first ) ); + glyph.display.push_back( static_cast<wchar_t>( first ) ); + bool representable = width > 0 && !u_hasBinaryProperty( first, UCHAR_DEFAULT_IGNORABLE_CODE_POINT ) + && !u_hasBinaryProperty( first, UCHAR_EMOJI_PRESENTATION ); + while ( utext_getNativeIndex( text.get() ) < end ) { + const auto codepoint = utext_next32( text.get() ); + glyph.display.push_back( static_cast<wchar_t>( codepoint ) ); + // ncurses accepts one spacing character followed by nonspacing marks. + // Joiners, selectors and extra spacing characters use one visible fallback. + representable = representable && ::wcwidth( static_cast<wchar_t>( codepoint ) ) == 0 + && u_charType( codepoint ) == U_NON_SPACING_MARK + && !u_hasBinaryProperty( codepoint, UCHAR_DEFAULT_IGNORABLE_CODE_POINT ); + } + if ( !representable || glyph.display.size() > glyph_capacity_ ) { + glyph.display = L"?"; + glyph.columns = 1; + } else { + glyph.columns = width; + } + } + if ( glyph.word != WordKind::Space ) { + if ( glyph.word == previous && glyph.word != WordKind::Ideograph ) { + result.words.back().end = glyph.bytes.end; + } else { + result.words.push_back( glyph.bytes ); + } + } + previous = glyph.word; + result.graphemes.push_back( std::move( glyph ) ); + } + return result; +} + +} // namespace ricochet::tui::detail |