Remove HTML entity parsing (#274)
## Summary * Remove HTML entity parsing * This has been completely useless since the introduction of expat * expat tries to parse all entities in the document, but only knows of HTML ones * Parsing will never end with HTML entities in the text, so the additional step to parse them that we had went completely unused * We should figure out the best way to parse that content in the future, but for now remove that module as it generates a lot of heap allocations with its map and strings
This commit is contained in:
Dave Allie
@@ -1,163 +0,0 @@
|
||||
// from
|
||||
// https://github.com/atomic14/diy-esp32-epub-reader/blob/2c2f57fdd7e2a788d14a0bcb26b9e845a47aac42/lib/Epub/RubbishHtmlParser/htmlEntities.cpp
|
||||
|
||||
#include "htmlEntities.h"
|
||||
|
||||
#include <cstring>
|
||||
#include <unordered_map>
|
||||
|
||||
const int MAX_ENTITY_LENGTH = 10;
|
||||
|
||||
// Use book: entities_ww2.epub to test this (Page 7: Entities parser test)
|
||||
// Note the supported keys are only in lowercase
|
||||
// Store the mappings in a unordered hash map
|
||||
static std::unordered_map<std::string, std::string> entity_lookup(
|
||||
{{""", "\""}, {"⁄", "⁄"}, {"&", "&"}, {"<", "<"}, {">", ">"},
|
||||
{"À", "À"}, {"Á", "Á"}, {"Â", "Â"}, {"Ã", "Ã"}, {"Ä", "Ä"},
|
||||
{"Å", "Å"}, {"Æ", "Æ"}, {"Ç", "Ç"}, {"È", "È"}, {"É", "É"},
|
||||
{"Ê", "Ê"}, {"Ë", "Ë"}, {"Ì", "Ì"}, {"Í", "Í"}, {"Î", "Î"},
|
||||
{"Ï", "Ï"}, {"Ð", "Ð"}, {"Ñ", "Ñ"}, {"Ò", "Ò"}, {"Ó", "Ó"},
|
||||
{"Ô", "Ô"}, {"Õ", "Õ"}, {"Ö", "Ö"}, {"Ø", "Ø"}, {"Ù", "Ù"},
|
||||
{"Ú", "Ú"}, {"Û", "Û"}, {"Ü", "Ü"}, {"Ý", "Ý"}, {"Þ", "Þ"},
|
||||
{"ß", "ß"}, {"à", "à"}, {"á", "á"}, {"â", "â"}, {"ã", "ã"},
|
||||
{"ä", "ä"}, {"å", "å"}, {"æ", "æ"}, {"ç", "ç"}, {"è", "è"},
|
||||
{"é", "é"}, {"ê", "ê"}, {"ë", "ë"}, {"ì", "ì"}, {"í", "í"},
|
||||
{"î", "î"}, {"ï", "ï"}, {"ð", "ð"}, {"ñ", "ñ"}, {"ò", "ò"},
|
||||
{"ó", "ó"}, {"ô", "ô"}, {"õ", "õ"}, {"ö", "ö"}, {"ø", "ø"},
|
||||
{"ù", "ù"}, {"ú", "ú"}, {"û", "û"}, {"ü", "ü"}, {"ý", "ý"},
|
||||
{"þ", "þ"}, {"ÿ", "ÿ"}, {" ", " "}, {"¡", "¡"}, {"¢", "¢"},
|
||||
{"£", "£"}, {"¤", "¤"}, {"¥", "¥"}, {"¦", "¦"}, {"§", "§"},
|
||||
{"¨", "¨"}, {"©", "©"}, {"ª", "ª"}, {"«", "«"}, {"¬", "¬"},
|
||||
{"­", ""}, {"®", "®"}, {"¯", "¯"}, {"°", "°"}, {"±", "±"},
|
||||
{"²", "²"}, {"³", "³"}, {"´", "´"}, {"µ", "µ"}, {"¶", "¶"},
|
||||
{"¸", "¸"}, {"¹", "¹"}, {"º", "º"}, {"»", "»"}, {"¼", "¼"},
|
||||
{"½", "½"}, {"¾", "¾"}, {"¿", "¿"}, {"×", "×"}, {"÷", "÷"},
|
||||
{"∀", "∀"}, {"∂", "∂"}, {"∃", "∃"}, {"∅", "∅"}, {"∇", "∇"},
|
||||
{"∈", "∈"}, {"∉", "∉"}, {"∋", "∋"}, {"∏", "∏"}, {"∑", "∑"},
|
||||
{"−", "−"}, {"∗", "∗"}, {"√", "√"}, {"∝", "∝"}, {"∞", "∞"},
|
||||
{"∠", "∠"}, {"∧", "∧"}, {"∨", "∨"}, {"∩", "∩"}, {"∪", "∪"},
|
||||
{"∫", "∫"}, {"∴", "∴"}, {"∼", "∼"}, {"≅", "≅"}, {"≈", "≈"},
|
||||
{"≠", "≠"}, {"≡", "≡"}, {"≤", "≤"}, {"≥", "≥"}, {"⊂", "⊂"},
|
||||
{"⊃", "⊃"}, {"⊄", "⊄"}, {"⊆", "⊆"}, {"⊇", "⊇"}, {"⊕", "⊕"},
|
||||
{"⊗", "⊗"}, {"⊥", "⊥"}, {"⋅", "⋅"}, {"Α", "Α"}, {"Β", "Β"},
|
||||
{"Γ", "Γ"}, {"Δ", "Δ"}, {"Ε", "Ε"}, {"Ζ", "Ζ"}, {"Η", "Η"},
|
||||
{"Θ", "Θ"}, {"Ι", "Ι"}, {"Κ", "Κ"}, {"Λ", "Λ"}, {"Μ", "Μ"},
|
||||
{"Ν", "Ν"}, {"Ξ", "Ξ"}, {"Ο", "Ο"}, {"Π", "Π"}, {"Ρ", "Ρ"},
|
||||
{"Σ", "Σ"}, {"Τ", "Τ"}, {"Υ", "Υ"}, {"Φ", "Φ"}, {"Χ", "Χ"},
|
||||
{"Ψ", "Ψ"}, {"Ω", "Ω"}, {"α", "α"}, {"β", "β"}, {"γ", "γ"},
|
||||
{"δ", "δ"}, {"ε", "ε"}, {"ζ", "ζ"}, {"η", "η"}, {"θ", "θ"},
|
||||
{"ι", "ι"}, {"κ", "κ"}, {"λ", "λ"}, {"μ", "μ"}, {"ν", "ν"},
|
||||
{"ξ", "ξ"}, {"ο", "ο"}, {"π", "π"}, {"ρ", "ρ"}, {"ς", "ς"},
|
||||
{"σ", "σ"}, {"τ", "τ"}, {"υ", "υ"}, {"φ", "φ"}, {"χ", "χ"},
|
||||
{"ψ", "ψ"}, {"ω", "ω"}, {"ϑ", "ϑ"}, {"ϒ", "ϒ"}, {"ϖ", "ϖ"},
|
||||
{"Œ", "Œ"}, {"œ", "œ"}, {"Š", "Š"}, {"š", "š"}, {"Ÿ", "Ÿ"},
|
||||
{"ƒ", "ƒ"}, {"ˆ", "ˆ"}, {"˜", "˜"}, {" ", ""}, {" ", ""},
|
||||
{" ", ""}, {"‌", ""}, {"‍", ""}, {"‎", ""}, {"‏", ""},
|
||||
{"–", "–"}, {"—", "—"}, {"‘", "‘"}, {"’", "’"}, {"‚", "‚"},
|
||||
{"“", "“"}, {"”", "”"}, {"„", "„"}, {"†", "†"}, {"‡", "‡"},
|
||||
{"•", "•"}, {"…", "…"}, {"‰", "‰"}, {"′", "′"}, {"″", "″"},
|
||||
{"‹", "‹"}, {"›", "›"}, {"‾", "‾"}, {"€", "€"}, {"™", "™"},
|
||||
{"←", "←"}, {"↑", "↑"}, {"→", "→"}, {"↓", "↓"}, {"↔", "↔"},
|
||||
{"↵", "↵"}, {"⌈", "⌈"}, {"⌉", "⌉"}, {"⌊", "⌊"}, {"⌋", "⌋"},
|
||||
{"◊", "◊"}, {"♠", "♠"}, {"♣", "♣"}, {"♥", "♥"}, {"♦", "♦"}});
|
||||
|
||||
// converts from a unicode code point to the utf8 equivalent
|
||||
void convert_to_utf8(const int code, std::string& res) {
|
||||
// convert to a utf8 sequence
|
||||
if (code < 0x80) {
|
||||
res += static_cast<char>(code);
|
||||
} else if (code < 0x800) {
|
||||
res += static_cast<char>(0xc0 | (code >> 6));
|
||||
res += static_cast<char>(0x80 | (code & 0x3f));
|
||||
} else if (code < 0x10000) {
|
||||
res += static_cast<char>(0xe0 | (code >> 12));
|
||||
res += static_cast<char>(0x80 | ((code >> 6) & 0x3f));
|
||||
res += static_cast<char>(0x80 | (code & 0x3f));
|
||||
} else if (code < 0x200000) {
|
||||
res += static_cast<char>(0xf0 | (code >> 18));
|
||||
res += static_cast<char>(0x80 | ((code >> 12) & 0x3f));
|
||||
res += static_cast<char>(0x80 | ((code >> 6) & 0x3f));
|
||||
res += static_cast<char>(0x80 | (code & 0x3f));
|
||||
} else if (code < 0x4000000) {
|
||||
res += static_cast<char>(0xf8 | (code >> 24));
|
||||
res += static_cast<char>(0x80 | ((code >> 18) & 0x3f));
|
||||
res += static_cast<char>(0x80 | ((code >> 12) & 0x3f));
|
||||
res += static_cast<char>(0x80 | ((code >> 6) & 0x3f));
|
||||
res += static_cast<char>(0x80 | (code & 0x3f));
|
||||
} else if (code < 0x80000000) {
|
||||
res += static_cast<char>(0xfc | (code >> 30));
|
||||
res += static_cast<char>(0x80 | ((code >> 24) & 0x3f));
|
||||
res += static_cast<char>(0x80 | ((code >> 18) & 0x3f));
|
||||
res += static_cast<char>(0x80 | ((code >> 12) & 0x3f));
|
||||
res += static_cast<char>(0x80 | ((code >> 6) & 0x3f));
|
||||
}
|
||||
}
|
||||
|
||||
// handles numeric entities - e.g. Ӓ or ሴ
|
||||
bool process_numeric_entity(const std::string& entity, std::string& res) {
|
||||
int code = 0;
|
||||
// is it hex?
|
||||
if (entity[2] == 'x' || entity[2] == 'X') {
|
||||
// parse the hex code
|
||||
code = strtol(entity.substr(3, entity.size() - 3).c_str(), nullptr, 16);
|
||||
} else {
|
||||
code = strtol(entity.substr(2, entity.size() - 3).c_str(), nullptr, 10);
|
||||
}
|
||||
if (code != 0) {
|
||||
// special handling for nbsp
|
||||
if (code == 0xA0) {
|
||||
res += " ";
|
||||
} else {
|
||||
convert_to_utf8(code, res);
|
||||
}
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
// handles named entities - e.g. &
|
||||
bool process_string_entity(const std::string& entity, std::string& res) {
|
||||
// it's a named entity - find it in the lookup table
|
||||
// find it in the map
|
||||
const auto it = entity_lookup.find(entity);
|
||||
if (it != entity_lookup.end()) {
|
||||
res += it->second;
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
// replace all the entities in the string
|
||||
std::string replaceHtmlEntities(const char* text) {
|
||||
std::string res;
|
||||
res.reserve(strlen(text));
|
||||
for (int i = 0; i < strlen(text); ++i) {
|
||||
bool flag = false;
|
||||
// do we have a potential entity?
|
||||
if (text[i] == '&') {
|
||||
// find the end of the entity
|
||||
int j = i + 1;
|
||||
while (j < strlen(text) && text[j] != ';' && j - i < MAX_ENTITY_LENGTH) {
|
||||
j++;
|
||||
}
|
||||
if (j - i > 2) {
|
||||
char entity[j - i + 1];
|
||||
strncpy(entity, text + i, j - i);
|
||||
// is it a numeric code?
|
||||
if (entity[1] == '#') {
|
||||
flag = process_numeric_entity(entity, res);
|
||||
} else {
|
||||
flag = process_string_entity(entity, res);
|
||||
}
|
||||
// skip past the entity if we successfully decoded it
|
||||
if (flag) {
|
||||
i = j;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (!flag) {
|
||||
res += text[i];
|
||||
}
|
||||
}
|
||||
return res;
|
||||
}
|
||||
@@ -1,7 +0,0 @@
|
||||
// from
|
||||
// https://github.com/atomic14/diy-esp32-epub-reader/blob/2c2f57fdd7e2a788d14a0bcb26b9e845a47aac42/lib/Epub/RubbishHtmlParser/htmlEntities.cpp
|
||||
|
||||
#pragma once
|
||||
#include <string>
|
||||
|
||||
std::string replaceHtmlEntities(const char* text);
|
||||
@@ -6,7 +6,6 @@
|
||||
#include <expat.h>
|
||||
|
||||
#include "../Page.h"
|
||||
#include "../htmlEntities.h"
|
||||
|
||||
const char* HEADER_TAGS[] = {"h1", "h2", "h3", "h4", "h5", "h6"};
|
||||
constexpr int NUM_HEADER_TAGS = sizeof(HEADER_TAGS) / sizeof(HEADER_TAGS[0]);
|
||||
@@ -130,7 +129,7 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
|
||||
// Currently looking at whitespace, if there's anything in the partWordBuffer, flush it
|
||||
if (self->partWordBufferIndex > 0) {
|
||||
self->partWordBuffer[self->partWordBufferIndex] = '\0';
|
||||
self->currentTextBlock->addWord(std::move(replaceHtmlEntities(self->partWordBuffer)), fontStyle);
|
||||
self->currentTextBlock->addWord(self->partWordBuffer, fontStyle);
|
||||
self->partWordBufferIndex = 0;
|
||||
}
|
||||
// Skip the whitespace char
|
||||
@@ -155,7 +154,7 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
|
||||
// If we're about to run out of space, then cut the word off and start a new one
|
||||
if (self->partWordBufferIndex >= MAX_WORD_SIZE) {
|
||||
self->partWordBuffer[self->partWordBufferIndex] = '\0';
|
||||
self->currentTextBlock->addWord(std::move(replaceHtmlEntities(self->partWordBuffer)), fontStyle);
|
||||
self->currentTextBlock->addWord(self->partWordBuffer, fontStyle);
|
||||
self->partWordBufferIndex = 0;
|
||||
}
|
||||
|
||||
@@ -197,7 +196,7 @@ void XMLCALL ChapterHtmlSlimParser::endElement(void* userData, const XML_Char* n
|
||||
}
|
||||
|
||||
self->partWordBuffer[self->partWordBufferIndex] = '\0';
|
||||
self->currentTextBlock->addWord(std::move(replaceHtmlEntities(self->partWordBuffer)), fontStyle);
|
||||
self->currentTextBlock->addWord(self->partWordBuffer, fontStyle);
|
||||
self->partWordBufferIndex = 0;
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user