RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-05-31 14:38:11 +00:00
Code Issues Activity Actions

LibPDF: Stop storing unicode code points in Encoding

Browse source 
In PDF's fonts, encoding objects are used to translate bytes into fonts'
glyphs. Glyphs (in the fonts we currently support) organise their glyphs
in such a way that they are accessed by name, and thus encoding
translate between a byte sequence and a glyph name.

Note that an no point this translation includes a Unicode character, and
therefore assigning a character to a glyph in the Encoding object is the
wrong thing to do. Moreover, using the code point for this character
during the byte-sequence-to-glyph translation sequence is double-wrong.

This commit removes the characters associated to each translation in the
built-in Encoding objects. In order to keep commits short and sweet, I'm
currently simply removing the character from the enumeration, leaving
the old structure this information was held on intact. Instead, I'm
filling the "code_point" member with a zero, and filling both mappings
(which will be changed later on too) with the glyph name and the
associated char code.
This commit is contained in:
Rodrigo Tobar 2023-01-23 21:49:59 +08:00 • committed by Andreas Kling
parent 5577d5f789
commit 2f773b3c5c
2 changed files with 626 additions and 632 deletions
Download patch file Download diff file Expand all files Collapse all files

42
Userland/Libraries/LibPDF/Encoding.cpp
View file

@ -79,10 +79,9 @@ NonnullRefPtr<Encoding> Encoding::standard_encoding()
{
static NonnullRefPtr<Encoding> encoding = adopt_ref(*new Encoding());
if (encoding->m_descriptors.is_empty()) {
#define ENUMERATE(string, name, standard_code, mac_code, win_code, pdf_code) \
auto name##_code_point = *Utf8View(string##sv).begin(); \
encoding->m_descriptors.set(standard_code, { string, name##_code_point }); \
encoding->m_name_mapping.set(#name, name##_code_point);
#define ENUMERATE(name, standard_code, mac_code, win_code, pdf_code) \
encoding->m_descriptors.set(standard_code, { #name, 0 }); \
encoding->m_name_mapping.set(#name, standard_code);
ENUMERATE_LATIN_CHARACTER_SET(ENUMERATE)
#undef ENUMERATE
}
@ -94,10 +93,9 @@ NonnullRefPtr<Encoding> Encoding::mac_encoding()
{
static NonnullRefPtr<Encoding> encoding = adopt_ref(*new Encoding());
if (encoding->m_descriptors.is_empty()) {
#define ENUMERATE(string, name, standard_code, mac_code, win_code, pdf_code) \
auto name##_code_point = *Utf8View(string##sv).begin(); \
encoding->m_descriptors.set(mac_code, { string, name##_code_point }); \
encoding->m_name_mapping.set(#name, name##_code_point);
#define ENUMERATE(name, standard_code, mac_code, win_code, pdf_code) \
encoding->m_descriptors.set(mac_code, { #name, 0 }); \
encoding->m_name_mapping.set(#name, mac_code);
ENUMERATE_LATIN_CHARACTER_SET(ENUMERATE)
#undef ENUMERATE
}
@ -109,10 +107,9 @@ NonnullRefPtr<Encoding> Encoding::windows_encoding()
{
static NonnullRefPtr<Encoding> encoding = adopt_ref(*new Encoding());
if (encoding->m_descriptors.is_empty()) {
#define ENUMERATE(string, name, standard_code, mac_code, win_code, pdf_code) \
auto name##_code_point = *Utf8View(string##sv).begin(); \
encoding->m_descriptors.set(win_code, { string, name##_code_point }); \
encoding->m_name_mapping.set(#name, name##_code_point);
#define ENUMERATE(name, standard_code, mac_code, win_code, pdf_code) \
encoding->m_descriptors.set(win_code, { #name, 0 }); \
encoding->m_name_mapping.set(#name, win_code);
ENUMERATE_LATIN_CHARACTER_SET(ENUMERATE)
#undef ENUMERATE
encoding->m_windows = true;
@ -125,10 +122,9 @@ NonnullRefPtr<Encoding> Encoding::pdf_doc_encoding()
{
static NonnullRefPtr<Encoding> encoding = adopt_ref(*new Encoding());
if (encoding->m_descriptors.is_empty()) {
#define ENUMERATE(string, name, standard_code, mac_code, win_code, pdf_code) \
auto name##_code_point = *Utf8View(string##sv).begin(); \
encoding->m_descriptors.set(pdf_code, { string, name##_code_point }); \
encoding->m_name_mapping.set(#name, name##_code_point);
#define ENUMERATE(name, standard_code, mac_code, win_code, pdf_code) \
encoding->m_descriptors.set(pdf_code, { #name, 0 }); \
encoding->m_name_mapping.set(#name, pdf_code);
ENUMERATE_LATIN_CHARACTER_SET(ENUMERATE)
#undef ENUMERATE
}
@ -140,10 +136,9 @@ NonnullRefPtr<Encoding> Encoding::symbol_encoding()
{
static NonnullRefPtr<Encoding> encoding = adopt_ref(*new Encoding());
if (encoding->m_descriptors.is_empty()) {
#define ENUMERATE(string, name, code) \
auto name##_code_point = *Utf8View(string##sv).begin(); \
encoding->m_descriptors.set(code, { string, name##_code_point }); \
encoding->m_name_mapping.set(#name, name##_code_point);
#define ENUMERATE(name, code) \
encoding->m_descriptors.set(code, { #name, 0 }); \
encoding->m_name_mapping.set(#name, code);
ENUMERATE_SYMBOL_CHARACTER_SET(ENUMERATE)
#undef ENUMERATE
}
@ -155,10 +150,9 @@ NonnullRefPtr<Encoding> Encoding::zapf_encoding()
{
static NonnullRefPtr<Encoding> encoding = adopt_ref(*new Encoding());
if (encoding->m_descriptors.is_empty()) {
#define ENUMERATE(string, name, code) \
auto name##_code_point = *Utf8View(string##sv).begin(); \
encoding->m_descriptors.set(code, { string, name##_code_point }); \
encoding->m_name_mapping.set(#name, name##_code_point);
#define ENUMERATE(name, code) \
encoding->m_descriptors.set(code, { #name, 0 }); \
encoding->m_name_mapping.set(#name, code);
ENUMERATE_ZAPF_DINGBATS_CHARACTER_SET(ENUMERATE)
#undef ENUMERATE
}