nokogumbo 2.0.0.pre.alpha → 2.0.0

data/gumbo-parser/src/tokenizer.h

@@ -44,7 +44,6 @@ typedef struct GumboInternalTokenEndTag {
   GumboTag tag;
   // NULL unless tag is GUMBO_TAG_UNKNOWN
   char *name;
-  bool is_self_closing;
 } GumboTokenEndTag;
 
 // A data structure representing a single token in the input stream. This
@@ -83,11 +82,12 @@ void gumbo_tokenizer_set_state (
   GumboTokenizerEnum state
 );
 
-// Flags whether the current node is a foreign content element. This is
-// necessary for the markup declaration open state, where the tokenizer must be
-// aware of the state of the parser to properly tokenize bad comment tags.
+// Flags whether the adjusted current node is a foreign content element. This
+// is necessary for the markup declaration open state, where the tokenizer
+// must be aware of the state of the parser to properly tokenize bad comment
+// tags.
 // https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state
-void gumbo_tokenizer_set_is_current_node_foreign (
+void gumbo_tokenizer_set_is_adjusted_current_node_foreign (
   struct GumboInternalParser* parser,
   bool is_foreign
 );

data/gumbo-parser/src/tokenizer_states.h

@@ -14,74 +14,326 @@
 // The ordering of this enum is also used to build the dispatch table for the
 // tokenizer state machine, so if it is changed, be sure to update that too.
 typedef enum {
+  // 12.2.5.1 Data state
+  // https://html.spec.whatwg.org/multipage/parsing.html#data-state
   GUMBO_LEX_DATA,
-  GUMBO_LEX_CHAR_REF_IN_DATA,
+
+  // 12.2.5.2 RCDATA state
+  // https://html.spec.whatwg.org/multipage/parsing.html#rcdata-state
   GUMBO_LEX_RCDATA,
-  GUMBO_LEX_CHAR_REF_IN_RCDATA,
+
+  // 12.2.5.3 RAWTEXT state
+  // https://html.spec.whatwg.org/multipage/parsing.html#rawtext-state<Paste>
   GUMBO_LEX_RAWTEXT,
-  GUMBO_LEX_SCRIPT,
+
+  // 12.2.5.4 Script data state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-state
+  GUMBO_LEX_SCRIPT_DATA,
+
+  // 12.2.5.5 PLAINTEXT state
+  // https://html.spec.whatwg.org/multipage/parsing.html#plaintext-state
   GUMBO_LEX_PLAINTEXT,
+
+  // 12.2.5.6 Tag open state
+  // https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
   GUMBO_LEX_TAG_OPEN,
+
+  // 12.2.5.7 End tag open state
+  // https://html.spec.whatwg.org/multipage/parsing.html#end-tag-open-state
   GUMBO_LEX_END_TAG_OPEN,
+
+  // 12.2.5.8 Tag name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#tag-name-state
   GUMBO_LEX_TAG_NAME,
+
+  // 12.2.5.9 RCDATA less-than sign state
+  // https://html.spec.whatwg.org/multipage/parsing.html#rcdata-less-than-sign-state
   GUMBO_LEX_RCDATA_LT,
+
+  // 12.2.5.10 RCDATA end tag open state
+  // https://html.spec.whatwg.org/multipage/parsing.html#rcdata-end-tag-open-state
   GUMBO_LEX_RCDATA_END_TAG_OPEN,
+
+  // 12.2.5.11 RCDATA end tag name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#rcdata-end-tag-name-state
   GUMBO_LEX_RCDATA_END_TAG_NAME,
+
+  // 12.2.5.12 RAWTEXT less-than sign state
+  // https://html.spec.whatwg.org/multipage/parsing.html#rawtext-less-than-sign-state
   GUMBO_LEX_RAWTEXT_LT,
+
+  // 12.2.5.13 RAWTEXT end tag open state
+  // https://html.spec.whatwg.org/multipage/parsing.html#rawtext-end-tag-open-state
   GUMBO_LEX_RAWTEXT_END_TAG_OPEN,
+
+  // 12.2.5.14 RAWTEXT end tag name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#rawtext-end-tag-name-state
   GUMBO_LEX_RAWTEXT_END_TAG_NAME,
-  GUMBO_LEX_SCRIPT_LT,
-  GUMBO_LEX_SCRIPT_END_TAG_OPEN,
-  GUMBO_LEX_SCRIPT_END_TAG_NAME,
-  GUMBO_LEX_SCRIPT_ESCAPED_START,
-  GUMBO_LEX_SCRIPT_ESCAPED_START_DASH,
-  GUMBO_LEX_SCRIPT_ESCAPED,
-  GUMBO_LEX_SCRIPT_ESCAPED_DASH,
-  GUMBO_LEX_SCRIPT_ESCAPED_DASH_DASH,
-  GUMBO_LEX_SCRIPT_ESCAPED_LT,
-  GUMBO_LEX_SCRIPT_ESCAPED_END_TAG_OPEN,
-  GUMBO_LEX_SCRIPT_ESCAPED_END_TAG_NAME,
-  GUMBO_LEX_SCRIPT_DOUBLE_ESCAPED_START,
-  GUMBO_LEX_SCRIPT_DOUBLE_ESCAPED,
-  GUMBO_LEX_SCRIPT_DOUBLE_ESCAPED_DASH,
-  GUMBO_LEX_SCRIPT_DOUBLE_ESCAPED_DASH_DASH,
-  GUMBO_LEX_SCRIPT_DOUBLE_ESCAPED_LT,
-  GUMBO_LEX_SCRIPT_DOUBLE_ESCAPED_END,
+
+  // 12.2.5.15 Script data less-than sign state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-less-than-sign-state
+  GUMBO_LEX_SCRIPT_DATA_LT,
+
+  // 12.2.5.16 Script data end tag open state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-end-tag-open-state
+  GUMBO_LEX_SCRIPT_DATA_END_TAG_OPEN,
+
+  // 12.2.5.17 Script data end tag name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-end-tag-name-state
+  GUMBO_LEX_SCRIPT_DATA_END_TAG_NAME,
+
+  // 12.2.5.18 Script data escape start state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escape-start-state
+  GUMBO_LEX_SCRIPT_DATA_ESCAPED_START,
+
+  // 12.2.5.19 Script data escape start dash state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escape-start-dash-state
+  GUMBO_LEX_SCRIPT_DATA_ESCAPED_START_DASH,
+
+  // 12.2.5.20 Script data escaped state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-state
+  GUMBO_LEX_SCRIPT_DATA_ESCAPED,
+
+  // 12.2.5.21 Script data escaped dash state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-dash-state
+  GUMBO_LEX_SCRIPT_DATA_ESCAPED_DASH,
+
+  // 12.2.5.22 Script data escaped dash dash state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-dash-dash-state
+  GUMBO_LEX_SCRIPT_DATA_ESCAPED_DASH_DASH,
+
+  // 12.2.5.23 Script data escaped less than sign state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-less-than-sign-state
+  GUMBO_LEX_SCRIPT_DATA_ESCAPED_LT,
+
+  // 12.2.5.24 Script data escaped end tag open state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-end-tag-open-state
+  GUMBO_LEX_SCRIPT_DATA_ESCAPED_END_TAG_OPEN,
+
+  // 12.2.5.25 Script data escaped end tag name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-end-tag-name-state
+  GUMBO_LEX_SCRIPT_DATA_ESCAPED_END_TAG_NAME,
+
+  // 12.2.5.26 Script data double escape start state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escape-start-state
+  GUMBO_LEX_SCRIPT_DATA_DOUBLE_ESCAPED_START,
+
+  // 12.2.5.27 Script data double escaped state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escaped-state
+  GUMBO_LEX_SCRIPT_DATA_DOUBLE_ESCAPED,
+
+  // 12.2.5.28 Script data double escaped dash state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escaped-dash-state
+  GUMBO_LEX_SCRIPT_DATA_DOUBLE_ESCAPED_DASH,
+
+  // 12.2.5.29 Script data double escaped dash dash state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escaped-dash-dash-state
+  GUMBO_LEX_SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH,
+
+  // 12.2.5.30 Script data double escaped less-than sign state
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escaped-less-than-sign-state
+  GUMBO_LEX_SCRIPT_DATA_DOUBLE_ESCAPED_LT,
+
+  // 12.2.5.31 Script data double escape end state (XXX: spec bug with the
+  // name?)
+  // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escape-end-state
+  GUMBO_LEX_SCRIPT_DATA_DOUBLE_ESCAPED_END,
+
+  // 12.2.5.32 Before attribute name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#before-attribute-name-state
   GUMBO_LEX_BEFORE_ATTR_NAME,
+
+  // 12.2.5.33 Attributet name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#attribute-name-state
   GUMBO_LEX_ATTR_NAME,
+
+  // 12.2.5.34 After attribute name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#after-attribute-name-state
   GUMBO_LEX_AFTER_ATTR_NAME,
+
+  // 12.2.5.35 Before attribute value state
+  // https://html.spec.whatwg.org/multipage/parsing.html#before-attribute-value-state
   GUMBO_LEX_BEFORE_ATTR_VALUE,
+
+  // 12.2.5.36 Attribute value (double-quoted) state
+  // https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(double-quoted)-state
   GUMBO_LEX_ATTR_VALUE_DOUBLE_QUOTED,
+
+  // 12.2.5.37 Attribute value (single-quoted) state
+  // https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(single-quoted)-state
   GUMBO_LEX_ATTR_VALUE_SINGLE_QUOTED,
+
+  // 12.2.5.38 Attribute value (unquoted) state
+  // https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(unquoted)-state
   GUMBO_LEX_ATTR_VALUE_UNQUOTED,
-  GUMBO_LEX_CHAR_REF_IN_ATTR_VALUE,
+
+  // 12.2.5.39 After attribute value (quoted) state
+  // https://html.spec.whatwg.org/multipage/parsing.html#after-attribute-value-(quoted)-state
   GUMBO_LEX_AFTER_ATTR_VALUE_QUOTED,
+
+  // 12.2.5.40 Self-closing start tag state
+  // https://html.spec.whatwg.org/multipage/parsing.html#self-closing-start-tag-state
   GUMBO_LEX_SELF_CLOSING_START_TAG,
+
+  // 12.2.5.41 Bogus comment state
+  // https://html.spec.whatwg.org/multipage/parsing.html#bogus-comment-state
   GUMBO_LEX_BOGUS_COMMENT,
-  GUMBO_LEX_MARKUP_DECLARATION,
+
+  // 12.2.5.42 Markup declaration open state
+  // https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state
+  GUMBO_LEX_MARKUP_DECLARATION_OPEN,
+
+  // 12.2.5.43 Comment start state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-start-state
   GUMBO_LEX_COMMENT_START,
+
+  // 12.2.5.44 Comment start dash state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-start-dash-state
   GUMBO_LEX_COMMENT_START_DASH,
+
+  // 12.2.5.45 Comment state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-state
   GUMBO_LEX_COMMENT,
+
+  // 12.2.5.46 Comment less-than sign state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-less-than-sign-state
+  GUMBO_LEX_COMMENT_LT,
+
+  // 12.2.5.47 Comment less-than sign bang state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-less-than-sign-bang-state
+  GUMBO_LEX_COMMENT_LT_BANG,
+
+  // 12.2.5.48 Comment less-than sign bang dash state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-less-than-sign-bang-dash-state
+  GUMBO_LEX_COMMENT_LT_BANG_DASH,
+
+  // 12.2.5.49 Comment less-than sign bang dash dash state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-less-than-sign-bang-dash-dash-state
+  GUMBO_LEX_COMMENT_LT_BANG_DASH_DASH,
+
+  // 12.2.5.50 Comment end dash state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-end-dash-state
   GUMBO_LEX_COMMENT_END_DASH,
+
+  // 12.2.5.51 Comment end state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-end-state
   GUMBO_LEX_COMMENT_END,
+
+  // 12.2.5.52 Comment end bang state
+  // https://html.spec.whatwg.org/multipage/parsing.html#comment-end-bang-state
   GUMBO_LEX_COMMENT_END_BANG,
+
+  // 12.2.5.53 DOCTYPE state
+  // https://html.spec.whatwg.org/multipage/parsing.html#doctype-state
   GUMBO_LEX_DOCTYPE,
+
+  // 12.2.5.54 Before DOCTYPE name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#before-doctype-name-state
   GUMBO_LEX_BEFORE_DOCTYPE_NAME,
+
+  // 12.2.5.55 DOCTYPE name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#doctype-name-state
   GUMBO_LEX_DOCTYPE_NAME,
+
+  // 12.2.5.56 After DOCTYPE name state
+  // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-name-state
   GUMBO_LEX_AFTER_DOCTYPE_NAME,
+
+  // 12.2.5.57 After DOCTYPE public keyword state
+  // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-public-keyword-state
   GUMBO_LEX_AFTER_DOCTYPE_PUBLIC_KEYWORD,
+
+  // 12.2.5.58 Before DOCTYPE public identifier state
+  // https://html.spec.whatwg.org/multipage/parsing.html#before-doctype-public-identifier-state
   GUMBO_LEX_BEFORE_DOCTYPE_PUBLIC_ID,
+
+  // 12.2.5.59 DOCTYPE public identifier (double-quoted) state
+  // https://html.spec.whatwg.org/multipage/parsing.html#doctype-public-identifier-(double-quoted)-state
   GUMBO_LEX_DOCTYPE_PUBLIC_ID_DOUBLE_QUOTED,
+
+  // 12.2.5.60 DOCTYPE public identifier (single-quoted) state
+  // https://html.spec.whatwg.org/multipage/parsing.html#doctype-public-identifier-(single-quoted)-state
   GUMBO_LEX_DOCTYPE_PUBLIC_ID_SINGLE_QUOTED,
+
+  // 12.2.5.61 After DOCTYPE public identifier state
+  // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-public-identifier-state
   GUMBO_LEX_AFTER_DOCTYPE_PUBLIC_ID,
+
+  // 12.2.5.62 Between DOCTYPE public and system identifiers state
+  // https://html.spec.whatwg.org/multipage/parsing.html#between-doctype-public-and-system-identifiers-state
   GUMBO_LEX_BETWEEN_DOCTYPE_PUBLIC_SYSTEM_ID,
+
+  // 12.2.5.63 After DOCTYPE system keyword state
+  // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-system-keyword-state
   GUMBO_LEX_AFTER_DOCTYPE_SYSTEM_KEYWORD,
+
+  // 12.2.5.64 Before DOCTYPE system identifier state
+  // https://html.spec.whatwg.org/multipage/parsing.html#before-doctype-system-identifier-state
   GUMBO_LEX_BEFORE_DOCTYPE_SYSTEM_ID,
+
+  // 12.2.5.65 DOCTYPE system identifier (double-quoted) state
+  // https://html.spec.whatwg.org/multipage/parsing.html#doctype-system-identifier-(double-quoted)-state
   GUMBO_LEX_DOCTYPE_SYSTEM_ID_DOUBLE_QUOTED,
+
+  // 12.2.5.66 DOCTYPE system identifier (single-quoted) state
+  // https://html.spec.whatwg.org/multipage/parsing.html#doctype-system-identifier-(single-quoted)-state
   GUMBO_LEX_DOCTYPE_SYSTEM_ID_SINGLE_QUOTED,
+
+  // 12.2.5.67 After DOCTYPE system identifier state
+  // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-system-identifier-state
   GUMBO_LEX_AFTER_DOCTYPE_SYSTEM_ID,
+
+  // 12.2.5.68 Bogus DOCTYPE state
+  // https://html.spec.whatwg.org/multipage/parsing.html#bogus-doctype-state
   GUMBO_LEX_BOGUS_DOCTYPE,
-  GUMBO_LEX_CDATA
+
+  // 12.2.5.69 CDATA section state
+  // https://html.spec.whatwg.org/multipage/parsing.html#cdata-section-state
+  GUMBO_LEX_CDATA_SECTION,
+
+  // 12.2.5.70 CDATA section bracket state
+  // https://html.spec.whatwg.org/multipage/parsing.html#cdata-section-bracket-state
+  GUMBO_LEX_CDATA_SECTION_BRACKET,
+
+  // 12.2.5.71 CDATA section end state
+  // https://html.spec.whatwg.org/multipage/parsing.html#cdata-section-end-state
+  GUMBO_LEX_CDATA_SECTION_END,
+
+  // 12.2.5.72 Character reference state
+  // https://html.spec.whatwg.org/multipage/parsing.html#character-reference-state
+  GUMBO_LEX_CHARACTER_REFERENCE,
+
+  // 12.2.5.73 Named character reference state
+  // https://html.spec.whatwg.org/multipage/parsing.html#named-character-reference-state
+  GUMBO_LEX_NAMED_CHARACTER_REFERENCE,
+
+  // 12.2.5.74 Ambiguous ampersand state
+  // https://html.spec.whatwg.org/multipage/parsing.html#ambiguous-ampersand-state
+  GUMBO_LEX_AMBIGUOUS_AMPERSAND,
+
+  // 12.2.5.75 Numeric character reference state
+  // https://html.spec.whatwg.org/multipage/parsing.html#numeric-character-reference-state
+  GUMBO_LEX_NUMERIC_CHARACTER_REFERENCE,
+
+  // 12.2.5.76 Hexadecimal character reference start state
+  // https://html.spec.whatwg.org/multipage/parsing.html#hexadecimal-character-reference-start-state
+  GUMBO_LEX_HEXADECIMAL_CHARACTER_REFERENCE_START,
+
+  // 12.2.5.77 Decimal character reference start state
+  // https://html.spec.whatwg.org/multipage/parsing.html#decimal-character-reference-start-state
+  GUMBO_LEX_DECIMAL_CHARACTER_REFERENCE_START,
+  
+  // 12.2.5.78 Hexadecimal character reference state
+  // https://html.spec.whatwg.org/multipage/parsing.html#hexadecimal-character-reference-state
+  GUMBO_LEX_HEXADECIMAL_CHARACTER_REFERENCE,
+  
+  // 12.2.5.79 Decimal character reference state
+  // https://html.spec.whatwg.org/multipage/parsing.html#decimal-character-reference-state
+  GUMBO_LEX_DECIMAL_CHARACTER_REFERENCE,
+
+  // 12.2.5.80 Numeric character reference end state
+  // https://html.spec.whatwg.org/multipage/parsing.html#numeric-character-reference-end-state
+  GUMBO_LEX_NUMERIC_CHARACTER_REFERENCE_END
 } GumboTokenizerEnum;
 
 #endif // GUMBO_TOKENIZER_STATES_H_

data/gumbo-parser/src/utf8.c

@@ -27,8 +27,6 @@
 #include "ascii.h"
 #include "vector.h"
 
-const int kUtf8ReplacementChar = 0xFFFD;
-
 // References:
 // * https://tools.ietf.org/html/rfc3629
 // * https://html.spec.whatwg.org/multipage/parsing.html#preprocessing-the-input-stream
@@ -100,16 +98,9 @@ static void add_error(Utf8Iterator* iter, GumboErrorType type) {
   }
   error->type = type;
   error->position = iter->_pos;
-  error->original_text = iter->_start;
-
-  // At the point the error is recorded, the code point hasn't been computed
-  // yet (and can't be, because it's invalid), so we need to build up the raw
-  // hex value from the bytes under the cursor.
-  uint32_t code_point = 0;
-  for (size_t i = 0; i < iter->_width; ++i) {
-    code_point = (code_point << 8) | (unsigned char) iter->_start[i];
-  }
-  error->v.codepoint = code_point;
+  error->original_text.data = iter->_start;
+  error->original_text.length = iter->_width;
+  error->v.tokenizer.codepoint = iter->_current;
 }
 
 // Reads the next UTF-8 character in the iter.
@@ -147,13 +138,15 @@ static void read_char(Utf8Iterator* iter) {
         }
         code_point = '\n';
       }
-      if (utf8_is_invalid_code_point(code_point)) {
-	// Invalid code points are errors, but they are not replaced by
-	// U+FFFD.
-	// https://html.spec.whatwg.org/multipage/parsing.html#preprocessing-the-input-stream
-        add_error(iter, GUMBO_ERR_UTF8_INVALID);
-      }
       iter->_current = code_point;
+      if (utf8_is_surrogate(code_point)) {
+	add_error(iter, GUMBO_ERR_SURROGATE_IN_INPUT_STREAM);
+      } else if (utf8_is_noncharacter(code_point)) {
+        add_error(iter, GUMBO_ERR_NONCHARACTER_IN_INPUT_STREAM);
+      } else if (utf8_is_control(code_point)
+                 && !(gumbo_ascii_isspace(code_point) || code_point == 0)) {
+        add_error(iter, GUMBO_ERR_CONTROL_CHARACTER_IN_INPUT_STREAM);
+      }
       return;
     } else if (state == UTF8_REJECT) {
       // We don't want to consume the invalid continuation byte of a multi-byte
@@ -169,8 +162,8 @@ static void read_char(Utf8Iterator* iter) {
   // rest of the iterator, and emit a replacement character. The next time we
   // enter this method, it will detect that there's no input to consume and
   // output an EOF.
-  iter->_current = kUtf8ReplacementChar;
   iter->_width = iter->_end - iter->_start;
+  iter->_current = kUtf8ReplacementChar;
   add_error(iter, GUMBO_ERR_UTF8_TRUNCATED);
 }
 
@@ -187,20 +180,6 @@ static void update_position(Utf8Iterator* iter) {
   }
 }
 
-// Returns true if this Unicode code point is in the list of characters
-// forbidden by the HTML5 spec, such as undefined control chars.
-bool utf8_is_invalid_code_point(int c) {
-  return
-    (c >= 0x1 && c <= 0x8)
-    || c == 0xB
-    || (c >= 0xE && c <= 0x1F)
-    || (c >= 0x7F && c <= 0x9F)
-    || (c >= 0xFDD0 && c <= 0xFDEF)
-    || ((c & 0xFFFF) == 0xFFFE)
-    || ((c & 0xFFFF) == 0xFFFF)
-  ;
-}
-
 void utf8iterator_init (
   GumboParser* parser,
   const char* source,
@@ -224,25 +203,6 @@ void utf8iterator_next(Utf8Iterator* iter) {
   read_char(iter);
 }
 
-int utf8iterator_current(const Utf8Iterator* iter) {
-  return iter->_current;
-}
-
-void utf8iterator_get_position (
-  const Utf8Iterator* iter,
-  GumboSourcePosition* output
-) {
-  *output = iter->_pos;
-}
-
-const char* utf8iterator_get_char_pointer(const Utf8Iterator* iter) {
-  return iter->_start;
-}
-
-const char* utf8iterator_get_end_pointer(const Utf8Iterator* iter) {
-  return iter->_end;
-}
-
 bool utf8iterator_maybe_consume_match (
   Utf8Iterator* iter,
   const char* prefix,
@@ -278,10 +238,3 @@ void utf8iterator_reset(Utf8Iterator* iter) {
   iter->_pos = iter->_mark_pos;
   read_char(iter);
 }
-
-// Sets the position and original text fields of an error to the value at the
-// mark.
-void utf8iterator_fill_error_at_mark(Utf8Iterator* iter, GumboError* error) {
-  error->position = iter->_mark_pos;
-  error->original_text = iter->_mark;
-}