fix: resolve early boot heap corruption via local static entities

lib/Epub/Epub/htmlEntities.cpp

@@ -11,55 +11,11 @@ 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(
+// static std::unordered_map<std::string, std::string> entity_lookup(...);
-    {{"&quot;", "\""},  {"&frasl;", "⁄"},   {"&amp;", "&"},      {"&lt;", "<"},     {"&gt;", ">"},
+// REFACTORED TO LOCAL STATIC: Global maps of strings trigger massive heap allocations
-     {"&Agrave;", "À"}, {"&Aacute;", "Á"},  {"&Acirc;", "Â"},    {"&Atilde;", "Ã"}, {"&Auml;", "Ä"},
+// during static initialization. On ESP32, this can occur before the heap/OS is
-     {"&Aring;", "Å"},  {"&AElig;", "Æ"},   {"&Ccedil;", "Ç"},   {"&Egrave;", "È"}, {"&Eacute;", "É"},
+// stable, leading to "Static Initialization Order Fiasco" and heap corruption.
-     {"&Ecirc;", "Ê"},  {"&Euml;", "Ë"},    {"&Igrave;", "Ì"},   {"&Iacute;", "Í"}, {"&Icirc;", "Î"},
+// Moving this inside the function ensures it's initialized safely on first use.
-     {"&Iuml;", "Ï"},   {"&ETH;", "Ð"},     {"&Ntilde;", "Ñ"},   {"&Ograve;", "Ò"}, {"&Oacute;", "Ó"},
-     {"&Ocirc;", "Ô"},  {"&Otilde;", "Õ"},  {"&Ouml;", "Ö"},     {"&Oslash;", "Ø"}, {"&Ugrave;", "Ù"},
-     {"&Uacute;", "Ú"}, {"&Ucirc;", "Û"},   {"&Uuml;", "Ü"},     {"&Yacute;", "Ý"}, {"&THORN;", "Þ"},
-     {"&szlig;", "ß"},  {"&agrave;", "à"},  {"&aacute;", "á"},   {"&acirc;", "â"},  {"&atilde;", "ã"},
-     {"&auml;", "ä"},   {"&aring;", "å"},   {"&aelig;", "æ"},    {"&ccedil;", "ç"}, {"&egrave;", "è"},
-     {"&eacute;", "é"}, {"&ecirc;", "ê"},   {"&euml;", "ë"},     {"&igrave;", "ì"}, {"&iacute;", "í"},
-     {"&icirc;", "î"},  {"&iuml;", "ï"},    {"&eth;", "ð"},      {"&ntilde;", "ñ"}, {"&ograve;", "ò"},
-     {"&oacute;", "ó"}, {"&ocirc;", "ô"},   {"&otilde;", "õ"},   {"&ouml;", "ö"},   {"&oslash;", "ø"},
-     {"&ugrave;", "ù"}, {"&uacute;", "ú"},  {"&ucirc;", "û"},    {"&uuml;", "ü"},   {"&yacute;", "ý"},
-     {"&thorn;", "þ"},  {"&yuml;", "ÿ"},    {"&nbsp;", " "},     {"&iexcl;", "¡"},  {"&cent;", "¢"},
-     {"&pound;", "£"},  {"&curren;", "¤"},  {"&yen;", "¥"},      {"&brvbar;", "¦"}, {"&sect;", "§"},
-     {"&uml;", "¨"},    {"&copy;", "©"},    {"&ordf;", "ª"},     {"&laquo;", "«"},  {"&not;", "¬"},
-     {"&shy;", "­"},    {"&reg;", "®"},     {"&macr;", "¯"},     {"&deg;", "°"},    {"&plusmn;", "±"},
-     {"&sup2;", "²"},   {"&sup3;", "³"},    {"&acute;", "´"},    {"&micro;", "µ"},  {"&para;", "¶"},
-     {"&cedil;", "¸"},  {"&sup1;", "¹"},    {"&ordm;", "º"},     {"&raquo;", "»"},  {"&frac14;", "¼"},
-     {"&frac12;", "½"}, {"&frac34;", "¾"},  {"&iquest;", "¿"},   {"&times;", "×"},  {"&divide;", "÷"},
-     {"&forall;", "∀"}, {"&part;", "∂"},    {"&exist;", "∃"},    {"&empty;", "∅"},  {"&nabla;", "∇"},
-     {"&isin;", "∈"},   {"&notin;", "∉"},   {"&ni;", "∋"},       {"&prod;", "∏"},   {"&sum;", "∑"},
-     {"&minus;", "−"},  {"&lowast;", "∗"},  {"&radic;", "√"},    {"&prop;", "∝"},   {"&infin;", "∞"},
-     {"&ang;", "∠"},    {"&and;", "∧"},     {"&or;", "∨"},       {"&cap;", "∩"},    {"&cup;", "∪"},
-     {"&int;", "∫"},    {"&there4;", "∴"},  {"&sim;", "∼"},      {"&cong;", "≅"},   {"&asymp;", "≈"},
-     {"&ne;", "≠"},     {"&equiv;", "≡"},   {"&le;", "≤"},       {"&ge;", "≥"},     {"&sub;", "⊂"},
-     {"&sup;", "⊃"},    {"&nsub;", "⊄"},    {"&sube;", "⊆"},     {"&supe;", "⊇"},   {"&oplus;", "⊕"},
-     {"&otimes;", "⊗"}, {"&perp;", "⊥"},    {"&sdot;", "⋅"},     {"&Alpha;", "Α"},  {"&Beta;", "Β"},
-     {"&Gamma;", "Γ"},  {"&Delta;", "Δ"},   {"&Epsilon;", "Ε"},  {"&Zeta;", "Ζ"},   {"&Eta;", "Η"},
-     {"&Theta;", "Θ"},  {"&Iota;", "Ι"},    {"&Kappa;", "Κ"},    {"&Lambda;", "Λ"}, {"&Mu;", "Μ"},
-     {"&Nu;", "Ν"},     {"&Xi;", "Ξ"},      {"&Omicron;", "Ο"},  {"&Pi;", "Π"},     {"&Rho;", "Ρ"},
-     {"&Sigma;", "Σ"},  {"&Tau;", "Τ"},     {"&Upsilon;", "Υ"},  {"&Phi;", "Φ"},    {"&Chi;", "Χ"},
-     {"&Psi;", "Ψ"},    {"&Omega;", "Ω"},   {"&alpha;", "α"},    {"&beta;", "β"},   {"&gamma;", "γ"},
-     {"&delta;", "δ"},  {"&epsilon;", "ε"}, {"&zeta;", "ζ"},     {"&eta;", "η"},    {"&theta;", "θ"},
-     {"&iota;", "ι"},   {"&kappa;", "κ"},   {"&lambda;", "λ"},   {"&mu;", "μ"},     {"&nu;", "ν"},
-     {"&xi;", "ξ"},     {"&omicron;", "ο"}, {"&pi;", "π"},       {"&rho;", "ρ"},    {"&sigmaf;", "ς"},
-     {"&sigma;", "σ"},  {"&tau;", "τ"},     {"&upsilon;", "υ"},  {"&phi;", "φ"},    {"&chi;", "χ"},
-     {"&psi;", "ψ"},    {"&omega;", "ω"},   {"&thetasym;", "ϑ"}, {"&upsih;", "ϒ"},  {"&piv;", "ϖ"},
-     {"&OElig;", "Œ"},  {"&oelig;", "œ"},   {"&Scaron;", "Š"},   {"&scaron;", "š"}, {"&Yuml;", "Ÿ"},
-     {"&fnof;", "ƒ"},   {"&circ;", "ˆ"},    {"&tilde;", "˜"},    {"&ensp;", ""},    {"&emsp;", ""},
-     {"&thinsp;", ""},  {"&zwnj;", "‌"},  {"&zwj;", "‍"},    {"&lrm;", "‎"},  {"&rlm;", "‏"},
-     {"&ndash;", "–"},  {"&mdash;", "—"},   {"&lsquo;", "‘"},    {"&rsquo;", "’"},  {"&sbquo;", "‚"},
-     {"&ldquo;", "“"},  {"&rdquo;", "”"},   {"&bdquo;", "„"},    {"&dagger;", "†"}, {"&Dagger;", "‡"},
-     {"&bull;", "•"},   {"&hellip;", "…"},  {"&permil;", "‰"},   {"&prime;", "′"},  {"&Prime;", "″"},
-     {"&lsaquo;", "‹"}, {"&rsaquo;", "›"},  {"&oline;", "‾"},    {"&euro;", "€"},   {"&trade;", "™"},
-     {"&larr;", "←"},   {"&uarr;", "↑"},    {"&rarr;", "→"},     {"&darr;", "↓"},   {"&harr;", "↔"},
-     {"&crarr;", "↵"},  {"&lceil;", "⌈"},   {"&rceil;", "⌉"},    {"&lfloor;", "⌊"}, {"&rfloor;", "⌋"},
-     {"&loz;", "◊"},    {"&spades;", "♠"},  {"&clubs;", "♣"},    {"&hearts;", "♥"}, {"&diams;", "♦"}});
 
 // converts from a unicode code point to the utf8 equivalent
 void convert_to_utf8(const int code, std::string& res) {
@@ -117,9 +73,60 @@ bool process_numeric_entity(const std::string& entity, std::string& res) {
 
 // handles named entities - e.g. &amp;
 bool process_string_entity(const std::string& entity, std::string& res) {
+  static const std::unordered_map<std::string, std::string> entity_lookup(
+      {{"&quot;", "\""},  {"&frasl;", "⁄"},   {"&amp;", "&"},      {"&lt;", "<"},     {"&gt;", ">"},
+       {"&Agrave;", "À"}, {"&Aacute;", "Á"},  {"&Acirc;", "Â"},    {"&Atilde;", "Ã"}, {"&Auml;", "Ä"},
+       {"&Aring;", "Å"},  {"&AElig;", "Æ"},   {"&Ccedil;", "Ç"},   {"&Egrave;", "È"}, {"&Eacute;", "É"},
+       {"&Ecirc;", "Ê"},  {"&Euml;", "Ë"},    {"&Igrave;", "Ì"},   {"&Iacute;", "Í"}, {"&Icirc;", "Î"},
+       {"&Iuml;", "Ï"},   {"&ETH;", "Ð"},     {"&Ntilde;", "Ñ"},   {"&Ograve;", "Ò"}, {"&Oacute;", "Ó"},
+       {"&Ocirc;", "Ô"},  {"&Otilde;", "Õ"},  {"&Ouml;", "Ö"},     {"&Oslash;", "Ø"}, {"&Ugrave;", "Ù"},
+       {"&Uacute;", "Ú"}, {"&Ucirc;", "Û"},   {"&Uuml;", "Ü"},     {"&Yacute;", "Ý"}, {"&THORN;", "Þ"},
+       {"&szlig;", "ß"},  {"&agrave;", "à"},  {"&aacute;", "á"},   {"&acirc;", "â"},  {"&atilde;", "ã"},
+       {"&auml;", "ä"},   {"&aring;", "å"},   {"&aelig;", "æ"},    {"&ccedil;", "ç"}, {"&egrave;", "è"},
+       {"&eacute;", "é"}, {"&ecirc;", "ê"},   {"&euml;", "ë"},     {"&igrave;", "ì"}, {"&iacute;", "í"},
+       {"&icirc;", "î"},  {"&iuml;", "ï"},    {"&eth;", "ð"},      {"&ntilde;", "ñ"}, {"&ograve;", "ò"},
+       {"&oacute;", "ó"}, {"&ocirc;", "ô"},   {"&otilde;", "õ"},   {"&ouml;", "ö"},   {"&oslash;", "ø"},
+       {"&ugrave;", "ù"}, {"&uacute;", "ú"},  {"&ucirc;", "û"},    {"&uuml;", "ü"},   {"&yacute;", "ý"},
+       {"&thorn;", "þ"},  {"&yuml;", "ÿ"},    {"&nbsp;", " "},     {"&iexcl;", "¡"},  {"&cent;", "¢"},
+       {"&pound;", "£"},  {"&curren;", "¤"},  {"&yen;", "¥"},      {"&brvbar;", "¦"}, {"&sect;", "§"},
+       {"&uml;", "¨"},    {"&copy;", "©"},    {"&ordf;", "ª"},     {"&laquo;", "«"},  {"&not;", "¬"},
+       {"&shy;", "­"},    {"&reg;", "®"},     {"&macr;", "¯"},     {"&deg;", "°"},    {"&plusmn;", "±"},
+       {"&sup2;", "²"},   {"&sup3;", "³"},    {"&acute;", "´"},    {"&micro;", "µ"},  {"&para;", "¶"},
+       {"&cedil;", "¸"},  {"&sup1;", "¹"},    {"&ordm;", "º"},     {"&raquo;", "»"},  {"&frac14;", "¼"},
+       {"&frac12;", "½"}, {"&frac34;", "¾"},  {"&iquest;", "¿"},   {"&times;", "×"},  {"&divide;", "÷"},
+       {"&forall;", "∀"}, {"&part;", "∂"},    {"&exist;", "∃"},    {"&empty;", "∅"},  {"&nabla;", "∇"},
+       {"&isin;", "∈"},   {"&notin;", "∉"},   {"&ni;", "∋"},       {"&prod;", "∏"},   {"&sum;", "∑"},
+       {"&minus;", "−"},  {"&lowast;", "∗"},  {"&radic;", "√"},    {"&prop;", "∝"},   {"&infin;", "∞"},
+       {"&ang;", "∠"},    {"&and;", "∧"},     {"&or;", "∨"},       {"&cap;", "∩"},    {"&cup;", "∪"},
+       {"&int;", "∫"},    {"&there4;", "∴"},  {"&sim;", "∼"},      {"&cong;", "≅"},   {"&asymp;", "≈"},
+       {"&ne;", "≠"},     {"&equiv;", "≡"},   {"&le;", "≤"},       {"&ge;", "≥"},     {"&sub;", "⊂"},
+       {"&sup;", "⊃"},    {"&nsub;", "⊄"},    {"&sube;", "⊆"},     {"&supe;", "⊇"},   {"&oplus;", "⊕"},
+       {"&otimes;", "⊗"}, {"&perp;", "⊥"},    {"&sdot;", "⋅"},     {"&Alpha;", "Α"},  {"&Beta;", "Β"},
+       {"&Gamma;", "Γ"},  {"&Delta;", "Δ"},   {"&Epsilon;", "Ε"},  {"&Zeta;", "Ζ"},   {"&Eta;", "Η"},
+       {"&Theta;", "Θ"},  {"&Iota;", "Ι"},    {"&Kappa;", "Κ"},    {"&Lambda;", "Λ"}, {"&Mu;", "Μ"},
+       {"&Nu;", "Ν"},     {"&Xi;", "Ξ"},      {"&Omicron;", "Ο"},  {"&Pi;", "Π"},     {"&Rho;", "Ρ"},
+       {"&Sigma;", "Σ"},  {"&Tau;", "Τ"},     {"&Upsilon;", "Υ"},  {"&Phi;", "Φ"},    {"&Chi;", "Χ"},
+       {"&Psi;", "Ψ"},    {"&Omega;", "Ω"},   {"&alpha;", "α"},    {"&beta;", "β"},   {"&gamma;", "γ"},
+       {"&delta;", "δ"},  {"&epsilon;", "ε"}, {"&zeta;", "ζ"},     {"&eta;", "η"},    {"&theta;", "θ"},
+       {"&iota;", "ι"},   {"&kappa;", "κ"},   {"&lambda;", "λ"},   {"&mu;", "μ"},     {"&nu;", "ν"},
+       {"&xi;", "ξ"},     {"&omicron;", "ο"}, {"&pi;", "π"},       {"&rho;", "ρ"},    {"&sigmaf;", "ς"},
+       {"&sigma;", "σ"},  {"&tau;", "Τ"},     {"&upsilon;", "υ"},  {"&phi;", "φ"},    {"&chi;", "χ"},
+       {"&psi;", "ψ"},    {"&omega;", "ω"},   {"&thetasym;", "ϑ"}, {"&upsih;", "ϒ"},  {"&piv;", "ϖ"},
+       {"&OElig;", "Œ"},  {"&oelig;", "œ"},   {"&Scaron;", "Š"},   {"&scaron;", "š"}, {"&Yuml;", "Ÿ"},
+       {"&fnof;", "ƒ"},   {"&circ;", "ˆ"},    {"&tilde;", "˜"},    {"&ensp;", ""},    {"&emsp;", ""},
+       {"&thinsp;", ""},  {"&zwnj;", "‌"},  {"&zwj;", "‍"},    {"&lrm;", "‎"},  {"&rlm;", "‏"},
+       {"&ndash;", "–"},  {"&mdash;", "—"},   {"&lsquo;", "‘"},    {"&rsquo;", "’"},  {"&sbquo;", "‚"},
+       {"&ldquo;", "“"},  {"&rdquo;", "”"},   {"&bdquo;", "„"},    {"&dagger;", "†"}, {"&Dagger;", "‡"},
+       {"&bull;", "•"},   {"&hellip;", "…"},  {"&permil;", "‰"},   {"&prime;", "′"},  {"&Prime;", "″"},
+       {"&lsaquo;", "‹"}, {"&rsaquo;", "›"},  {"&oline;", "‾"},    {"&euro;", "€"},   {"&trade;", "™"},
+       {"&larr;", "←"},   {"&uarr;", "↑"},    {"&rarr;", "→"},     {"&darr;", "↓"},   {"&harr;", "↔"},
+       {"&crarr;", "↵"},  {"&lceil;", "⌈"},   {"&rceil;", "⌉"},    {"&lfloor;", "⌊"}, {"&rfloor;", "⌋"},
+       {"&loz;", "◊"},    {"&spades;", "♠"},  {"&clubs;", "♣"},    {"&hearts;", "♥"}, {"&diams;", "♦"}});
+
   // 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;

src/main.cpp

@@ -252,6 +252,16 @@ void setupDisplayAndFonts() {
 void setup() {
   t1 = millis();
 
+  // Check heap integrity after potential static initialization issues.
+  // If corruption is found, we surface it to the display and stop.
+  if (!heap_caps_check_integrity_all(true)) {
+    Serial.println("!!! HEAP CORRUPTION DETECTED AT BOOT !!!");
+    setupDisplayAndFonts();
+    exitActivity();
+    enterNewActivity(new FullScreenMessageActivity(renderer, mappedInputManager, "Heap corruption", EpdFontFamily::BOLD));
+    return;
+  }
+
   // Only start serial if USB connected
   pinMode(UART0_RXD, INPUT);
   if (digitalRead(UART0_RXD) == HIGH) {