Zach Nelson
333286acfc
## Summary Simplify code calculating compile-time array sizes with `sizeof(array)/sizeof(element)` to use `std::size`. --- ### AI Usage While CrossPoint doesn't have restrictions on AI tools in contributing, please be transparent about their usage as it helps set the right context for reviewers. Did you use AI tools to help write this code? _**PARTIALLY**_
114 lines
7.2 KiB
C++
114 lines
7.2 KiB
C++
// based on
|
||
// https://github.com/atomic14/diy-esp32-epub-reader/blob/2c2f57fdd7e2a788d14a0bcb26b9e845a47aac42/lib/Epub/RubbishHtmlParser/htmlEntities.cpp
|
||
|
||
#include "htmlEntities.h"
|
||
|
||
#include <cstring>
|
||
#include <iterator>
|
||
|
||
struct EntityPair {
|
||
const char* key;
|
||
const char* value;
|
||
};
|
||
|
||
// Sorted lexicographically by key to allow binary search.
|
||
static constexpr EntityPair ENTITY_LOOKUP[] = {
|
||
{"Æ", "Æ"}, {"Á", "Á"}, {"Â", "Â"}, {"À", "À"}, {"Α", "Α"},
|
||
{"Å", "Å"}, {"Ã", "Ã"}, {"Ä", "Ä"}, {"Β", "Β"}, {"Ç", "Ç"},
|
||
{"Χ", "Χ"}, {"‡", "‡"}, {"Δ", "Δ"}, {"Ð", "Ð"}, {"É", "É"},
|
||
{"Ê", "Ê"}, {"È", "È"}, {"Ε", "Ε"}, {"Η", "Η"}, {"Ë", "Ë"},
|
||
{"Γ", "Γ"}, {"Í", "Í"}, {"Î", "Î"}, {"Ì", "Ì"}, {"Ι", "Ι"},
|
||
{"Ï", "Ï"}, {"Κ", "Κ"}, {"Λ", "Λ"}, {"Μ", "Μ"}, {"Ñ", "Ñ"},
|
||
{"Ν", "Ν"}, {"Œ", "Œ"}, {"Ó", "Ó"}, {"Ô", "Ô"}, {"Ò", "Ò"},
|
||
{"Ω", "Ω"}, {"Ο", "Ο"}, {"Ø", "Ø"}, {"Õ", "Õ"}, {"Ö", "Ö"},
|
||
{"Φ", "Φ"}, {"Π", "Π"}, {"″", "″"}, {"Ψ", "Ψ"}, {"Ρ", "Ρ"},
|
||
{"Š", "Š"}, {"Σ", "Σ"}, {"Þ", "Þ"}, {"Τ", "Τ"}, {"Θ", "Θ"},
|
||
{"Ú", "Ú"}, {"Û", "Û"}, {"Ù", "Ù"}, {"Υ", "Υ"}, {"Ü", "Ü"},
|
||
{"Ξ", "Ξ"}, {"Ý", "Ý"}, {"Ÿ", "Ÿ"}, {"Ζ", "Ζ"}, {"á", "á"},
|
||
{"â", "â"}, {"´", "´"}, {"æ", "æ"}, {"à", "à"}, {"α", "α"},
|
||
{"&", "&"}, {"∧", "∧"}, {"∠", "∠"}, {"å", "å"}, {"≈", "≈"},
|
||
{"ã", "ã"}, {"ä", "ä"}, {"„", "„"}, {"β", "β"}, {"¦", "¦"},
|
||
{"•", "•"}, {"∩", "∩"}, {"ç", "ç"}, {"¸", "¸"}, {"¢", "¢"},
|
||
{"χ", "χ"}, {"ˆ", "ˆ"}, {"♣", "♣"}, {"≅", "≅"}, {"©", "©"},
|
||
{"↵", "↵"}, {"∪", "∪"}, {"¤", "¤"}, {"†", "†"}, {"↓", "↓"},
|
||
{"°", "°"}, {"δ", "δ"}, {"♦", "♦"}, {"÷", "÷"}, {"é", "é"},
|
||
{"ê", "ê"}, {"è", "è"}, {"∅", "∅"}, {" ", " "}, {" ", " "},
|
||
{"ε", "ε"}, {"≡", "≡"}, {"η", "η"}, {"ð", "ð"}, {"ë", "ë"},
|
||
{"€", "€"}, {"∃", "∃"}, {"ƒ", "ƒ"}, {"∀", "∀"}, {"½", "½"},
|
||
{"¼", "¼"}, {"¾", "¾"}, {"⁄", "⁄"}, {"γ", "γ"}, {"≥", "≥"},
|
||
{">", ">"}, {"↔", "↔"}, {"♥", "♥"}, {"…", "…"}, {"í", "í"},
|
||
{"î", "î"}, {"¡", "¡"}, {"ì", "ì"}, {"∞", "∞"}, {"∫", "∫"},
|
||
{"ι", "ι"}, {"¿", "¿"}, {"∈", "∈"}, {"ï", "ï"}, {"κ", "κ"},
|
||
{"λ", "λ"}, {"«", "«"}, {"←", "←"}, {"⌈", "⌈"}, {"“", "\u201C"},
|
||
{"≤", "≤"}, {"⌊", "⌊"}, {"∗", "∗"}, {"◊", "◊"}, {"‎", "\u200E"},
|
||
{"‹", "‹"}, {"‘", "\u2018"}, {"<", "<"}, {"¯", "¯"}, {"—", "—"},
|
||
{"µ", "µ"}, {"−", "−"}, {"μ", "μ"}, {"∇", "∇"}, {" ", "\xC2\xA0"},
|
||
{"–", "–"}, {"≠", "≠"}, {"∋", "∋"}, {"¬", "¬"}, {"∉", "∉"},
|
||
{"⊄", "⊄"}, {"ñ", "ñ"}, {"ν", "ν"}, {"ó", "ó"}, {"ô", "ô"},
|
||
{"œ", "œ"}, {"ò", "ò"}, {"‾", "‾"}, {"ω", "ω"}, {"ο", "ο"},
|
||
{"⊕", "⊕"}, {"∨", "∨"}, {"ª", "ª"}, {"º", "º"}, {"ø", "ø"},
|
||
{"õ", "õ"}, {"⊗", "⊗"}, {"ö", "ö"}, {"¶", "¶"}, {"∂", "∂"},
|
||
{"‰", "‰"}, {"⊥", "⊥"}, {"φ", "φ"}, {"π", "π"}, {"ϖ", "ϖ"},
|
||
{"±", "±"}, {"£", "£"}, {"′", "′"}, {"∏", "∏"}, {"∝", "∝"},
|
||
{"ψ", "ψ"}, {""", "\""}, {"√", "√"}, {"»", "»"}, {"→", "→"},
|
||
{"⌉", "⌉"}, {"”", "\u201D"}, {"®", "®"}, {"⌋", "⌋"}, {"ρ", "ρ"},
|
||
{"‏", "\u200F"}, {"›", "›"}, {"’", "\u2019"}, {"‚", "‚"}, {"š", "š"},
|
||
{"⋅", "⋅"}, {"§", "§"}, {"­", "\xC2\xAD"}, {"σ", "σ"}, {"ς", "ς"},
|
||
{"∼", "∼"}, {"♠", "♠"}, {"⊂", "⊂"}, {"⊆", "⊆"}, {"∑", "∑"},
|
||
{"¹", "¹"}, {"²", "²"}, {"³", "³"}, {"⊃", "⊃"}, {"⊇", "⊇"},
|
||
{"ß", "ß"}, {"τ", "τ"}, {"∴", "∴"}, {"θ", "θ"}, {"ϑ", "ϑ"},
|
||
{" ", " "}, {"þ", "þ"}, {"˜", "˜"}, {"×", "×"}, {"™", "™"},
|
||
{"ú", "ú"}, {"↑", "↑"}, {"û", "û"}, {"ù", "ù"}, {"¨", "¨"},
|
||
{"ϒ", "ϒ"}, {"υ", "υ"}, {"ü", "ü"}, {"ξ", "ξ"}, {"ý", "ý"},
|
||
{"¥", "¥"}, {"ÿ", "ÿ"}, {"ζ", "ζ"}, {"‍", "\u200D"}, {"‌", "\u200C"},
|
||
};
|
||
|
||
// Verify the table is sorted at compile time.
|
||
static constexpr int constexprStrcmp(const char* a, const char* b) {
|
||
for (size_t i = 0;; i++) {
|
||
if (a[i] != b[i]) return (unsigned char)a[i] < (unsigned char)b[i] ? -1 : 1;
|
||
if (a[i] == '\0') return 0;
|
||
}
|
||
}
|
||
|
||
static constexpr bool isTableSorted() {
|
||
for (size_t i = 1; i < std::size(ENTITY_LOOKUP); i++) {
|
||
if (constexprStrcmp(ENTITY_LOOKUP[i - 1].key, ENTITY_LOOKUP[i].key) >= 0) return false;
|
||
}
|
||
return true;
|
||
}
|
||
static_assert(isTableSorted(), "ENTITY_LOOKUP must be sorted lexicographically by key");
|
||
|
||
// Lookup a single HTML entity and return its UTF-8 value.
|
||
const char* lookupHtmlEntity(const char* entity, size_t len) {
|
||
if (entity == nullptr || len == 0) return nullptr;
|
||
|
||
size_t lo = 0;
|
||
size_t hi = std::size(ENTITY_LOOKUP);
|
||
|
||
while (lo < hi) {
|
||
const size_t mid = lo + (hi - lo) / 2;
|
||
const char* key = ENTITY_LOOKUP[mid].key;
|
||
const size_t keyLen = strlen(key);
|
||
const size_t cmpLen = (len < keyLen) ? len : keyLen;
|
||
int cmp = memcmp(entity, key, cmpLen);
|
||
if (cmp == 0) {
|
||
// safety net: if prefix equal, shorter string is considered smaller
|
||
if (len < keyLen)
|
||
cmp = -1;
|
||
else if (len > keyLen)
|
||
cmp = 1;
|
||
else
|
||
cmp = 0;
|
||
}
|
||
|
||
if (cmp == 0) return ENTITY_LOOKUP[mid].value;
|
||
if (cmp < 0)
|
||
hi = mid;
|
||
else
|
||
lo = mid + 1;
|
||
}
|
||
|
||
return nullptr;
|
||
}
|