HTML syntax highlighting

8 files changed, 224 insertions, 23 deletions

diff --git a/Makefile b/Makefile
index c7559c0..c34498a 100644
--- a/Makefile
+++ b/Makefile
@@ -31,7 +31,8 @@ libpcre2-32.a: pcre2-10.36.zip
 	unzip pcre2-10.36.zip
 	cd pcre2-10.36 && cmake -DPCRE2_BUILD_PCRE2_32=ON . && $(MAKE) -j8
 	cp pcre2-10.36/libpcre2-32.a ./
-
+keywords.h: keywords.py
+	./keywords.py
 ted.deb: release
 	rm -rf /tmp/ted
 	mkdir -p /tmp/ted/DEBIAN
diff --git a/README.md b/README.md
index 04eb29b..054ce0e 100644
--- a/README.md
+++ b/README.md
@@ -23,7 +23,7 @@ in other editors.
 - Multiple tabs, each with a different file
 - Split screen (default: Ctrl+\\, Ctrl+Shift+\\)
 - Auto-indent
-- Syntax highlighting for C, C++, Rust, Python, and LaTeX.
+- Syntax highlighting for C, C++, Rust, Python, LaTeX, and Markdown.
 - Find and replace (with regular expressions!)
 - Run build command (F4), go to errors
 - Run any shell command (Ctrl+!)
diff --git a/keywords.h b/keywords.h
index 5906c6f..5fdb0e5 100644
--- a/keywords.h
+++ b/keywords.h
@@ -179,3 +179,27 @@ static Keyword const *const syntax_all_keywords_python[] = {
 	['A'] = syntax_keywords_python_A, ['B'] = syntax_keywords_python_B, ['C'] = syntax_keywords_python_C, ['D'] = syntax_keywords_python_D, ['E'] = syntax_keywords_python_E, ['F'] = syntax_keywords_python_F, ['G'] = syntax_keywords_python_G, ['I'] = syntax_keywords_python_I, ['K'] = syntax_keywords_python_K, ['L'] = syntax_keywords_python_L, ['M'] = syntax_keywords_python_M, ['N'] = syntax_keywords_python_N, ['O'] = syntax_keywords_python_O, ['P'] = syntax_keywords_python_P, ['R'] = syntax_keywords_python_R, ['S'] = syntax_keywords_python_S, ['T'] = syntax_keywords_python_T, ['U'] = syntax_keywords_python_U, ['V'] = syntax_keywords_python_V, ['W'] = syntax_keywords_python_W, ['Z'] = syntax_keywords_python_Z, ['_'] = syntax_keywords_python__, ['a'] = syntax_keywords_python_a, ['b'] = syntax_keywords_python_b, ['c'] = syntax_keywords_python_c, ['d'] = syntax_keywords_python_d, ['e'] = syntax_keywords_python_e, ['f'] = syntax_keywords_python_f, ['g'] = syntax_keywords_python_g, ['h'] = syntax_keywords_python_h, ['i'] = syntax_keywords_python_i, ['l'] = syntax_keywords_python_l, ['m'] = syntax_keywords_python_m, ['n'] = syntax_keywords_python_n, ['o'] = syntax_keywords_python_o, ['p'] = syntax_keywords_python_p, ['q'] = syntax_keywords_python_q, ['r'] = syntax_keywords_python_r, ['s'] = syntax_keywords_python_s, ['t'] = syntax_keywords_python_t, ['v'] = syntax_keywords_python_v, ['w'] = syntax_keywords_python_w, ['y'] = syntax_keywords_python_y, ['z'] = syntax_keywords_python_z
 };
 
+static Keyword const syntax_keywords_html_a[11] = {{"accept-charset=", SYNTAX_BUILTIN},{"accept=", SYNTAX_BUILTIN},{"accesskey=", SYNTAX_BUILTIN},{"action=", SYNTAX_BUILTIN},{"align=", SYNTAX_BUILTIN},{"alt=", SYNTAX_BUILTIN},{"async=", SYNTAX_BUILTIN},{"autocomplete=", SYNTAX_BUILTIN},{"autofocus=", SYNTAX_BUILTIN},{"autoplay=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_b[3] = {{"bgcolor=", SYNTAX_BUILTIN},{"border=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_c[12] = {{"charset=", SYNTAX_BUILTIN},{"checked=", SYNTAX_BUILTIN},{"cite=", SYNTAX_BUILTIN},{"class=", SYNTAX_BUILTIN},{"color=", SYNTAX_BUILTIN},{"cols=", SYNTAX_BUILTIN},{"colspan=", SYNTAX_BUILTIN},{"content=", SYNTAX_BUILTIN},{"contenteditable=", SYNTAX_BUILTIN},{"controls=", SYNTAX_BUILTIN},{"coords=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_d[10] = {{"data=", SYNTAX_BUILTIN},{"datetime=", SYNTAX_BUILTIN},{"default=", SYNTAX_BUILTIN},{"defer=", SYNTAX_BUILTIN},{"dir=", SYNTAX_BUILTIN},{"dirname=", SYNTAX_BUILTIN},{"disabled=", SYNTAX_BUILTIN},{"download=", SYNTAX_BUILTIN},{"draggable=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_e[2] = {{"enctype=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_f[4] = {{"for=", SYNTAX_BUILTIN},{"form=", SYNTAX_BUILTIN},{"formaction=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_h[8] = {{"headers=", SYNTAX_BUILTIN},{"height=", SYNTAX_BUILTIN},{"hidden=", SYNTAX_BUILTIN},{"high=", SYNTAX_BUILTIN},{"href=", SYNTAX_BUILTIN},{"hreflang=", SYNTAX_BUILTIN},{"http-equiv=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_i[3] = {{"id=", SYNTAX_BUILTIN},{"ismap=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_k[2] = {{"kind=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_l[6] = {{"label=", SYNTAX_BUILTIN},{"lang=", SYNTAX_BUILTIN},{"list=", SYNTAX_BUILTIN},{"loop=", SYNTAX_BUILTIN},{"low=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_m[8] = {{"max=", SYNTAX_BUILTIN},{"maxlength=", SYNTAX_BUILTIN},{"media=", SYNTAX_BUILTIN},{"method=", SYNTAX_BUILTIN},{"min=", SYNTAX_BUILTIN},{"multiple=", SYNTAX_BUILTIN},{"muted=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_n[3] = {{"name=", SYNTAX_BUILTIN},{"novalidate=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_o[73] = {{"onabort=", SYNTAX_BUILTIN},{"onafterprint=", SYNTAX_BUILTIN},{"onbeforeprint=", SYNTAX_BUILTIN},{"onbeforeunload=", SYNTAX_BUILTIN},{"onblur=", SYNTAX_BUILTIN},{"oncanplay=", SYNTAX_BUILTIN},{"oncanplaythrough=", SYNTAX_BUILTIN},{"onchange=", SYNTAX_BUILTIN},{"onclick=", SYNTAX_BUILTIN},{"oncontextmenu=", SYNTAX_BUILTIN},{"oncopy=", SYNTAX_BUILTIN},{"oncuechange=", SYNTAX_BUILTIN},{"oncut=", SYNTAX_BUILTIN},{"ondblclick=", SYNTAX_BUILTIN},{"ondrag=", SYNTAX_BUILTIN},{"ondragend=", SYNTAX_BUILTIN},{"ondragenter=", SYNTAX_BUILTIN},{"ondragleave=", SYNTAX_BUILTIN},{"ondragover=", SYNTAX_BUILTIN},{"ondragstart=", SYNTAX_BUILTIN},{"ondrop=", SYNTAX_BUILTIN},{"ondurationchange=", SYNTAX_BUILTIN},{"onemptied=", SYNTAX_BUILTIN},{"onended=", SYNTAX_BUILTIN},{"onerror=", SYNTAX_BUILTIN},{"onfocus=", SYNTAX_BUILTIN},{"onhashchange=", SYNTAX_BUILTIN},{"oninput=", SYNTAX_BUILTIN},{"oninvalid=", SYNTAX_BUILTIN},{"onkeydown=", SYNTAX_BUILTIN},{"onkeypress=", SYNTAX_BUILTIN},{"onkeyup=", SYNTAX_BUILTIN},{"onload=", SYNTAX_BUILTIN},{"onloadeddata=", SYNTAX_BUILTIN},{"onloadedmetadata=", SYNTAX_BUILTIN},{"onloadstart=", SYNTAX_BUILTIN},{"onmousedown=", SYNTAX_BUILTIN},{"onmousemove=", SYNTAX_BUILTIN},{"onmouseout=", SYNTAX_BUILTIN},{"onmouseover=", SYNTAX_BUILTIN},{"onmouseup=", SYNTAX_BUILTIN},{"onmousewheel=", SYNTAX_BUILTIN},{"onoffline=", SYNTAX_BUILTIN},{"ononline=", SYNTAX_BUILTIN},{"onpagehide=", SYNTAX_BUILTIN},{"onpageshow=", SYNTAX_BUILTIN},{"onpaste=", SYNTAX_BUILTIN},{"onpause=", SYNTAX_BUILTIN},{"onplay=", SYNTAX_BUILTIN},{"onplaying=", SYNTAX_BUILTIN},{"onpopstate=", SYNTAX_BUILTIN},{"onprogress=", SYNTAX_BUILTIN},{"onratechange=", SYNTAX_BUILTIN},{"onreset=", SYNTAX_BUILTIN},{"onresize=", SYNTAX_BUILTIN},{"onscroll=", SYNTAX_BUILTIN},{"onsearch=", SYNTAX_BUILTIN},{"onseeked=", SYNTAX_BUILTIN},{"onseeking=", SYNTAX_BUILTIN},{"onselect=", SYNTAX_BUILTIN},{"onstalled=", SYNTAX_BUILTIN},{"onstorage=", SYNTAX_BUILTIN},{"onsubmit=", SYNTAX_BUILTIN},{"onsuspend=", SYNTAX_BUILTIN},{"ontimeupdate=", SYNTAX_BUILTIN},{"ontoggle=", SYNTAX_BUILTIN},{"onunload=", SYNTAX_BUILTIN},{"onvolumechange=", SYNTAX_BUILTIN},{"onwaiting=", SYNTAX_BUILTIN},{"onwheel=", SYNTAX_BUILTIN},{"open=", SYNTAX_BUILTIN},{"optimum=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_p[5] = {{"pattern=", SYNTAX_BUILTIN},{"placeholder=", SYNTAX_BUILTIN},{"poster=", SYNTAX_BUILTIN},{"preload=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_r[7] = {{"readonly=", SYNTAX_BUILTIN},{"rel=", SYNTAX_BUILTIN},{"required=", SYNTAX_BUILTIN},{"reversed=", SYNTAX_BUILTIN},{"rows=", SYNTAX_BUILTIN},{"rowspan=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_s[16] = {{"sandbox=", SYNTAX_BUILTIN},{"scope=", SYNTAX_BUILTIN},{"selected=", SYNTAX_BUILTIN},{"shape=", SYNTAX_BUILTIN},{"size=", SYNTAX_BUILTIN},{"sizes=", SYNTAX_BUILTIN},{"span=", SYNTAX_BUILTIN},{"spellcheck=", SYNTAX_BUILTIN},{"src=", SYNTAX_BUILTIN},{"srcdoc=", SYNTAX_BUILTIN},{"srclang=", SYNTAX_BUILTIN},{"srcset=", SYNTAX_BUILTIN},{"start=", SYNTAX_BUILTIN},{"step=", SYNTAX_BUILTIN},{"style=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_t[6] = {{"tabindex=", SYNTAX_BUILTIN},{"target=", SYNTAX_BUILTIN},{"title=", SYNTAX_BUILTIN},{"translate=", SYNTAX_BUILTIN},{"type=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_u[2] = {{"usemap=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_v[2] = {{"value=", SYNTAX_BUILTIN}};
+static Keyword const syntax_keywords_html_w[3] = {{"width=", SYNTAX_BUILTIN},{"wrap=", SYNTAX_BUILTIN}};
+static Keyword const *const syntax_all_keywords_html[] = {
+	['a'] = syntax_keywords_html_a, ['b'] = syntax_keywords_html_b, ['c'] = syntax_keywords_html_c, ['d'] = syntax_keywords_html_d, ['e'] = syntax_keywords_html_e, ['f'] = syntax_keywords_html_f, ['h'] = syntax_keywords_html_h, ['i'] = syntax_keywords_html_i, ['k'] = syntax_keywords_html_k, ['l'] = syntax_keywords_html_l, ['m'] = syntax_keywords_html_m, ['n'] = syntax_keywords_html_n, ['o'] = syntax_keywords_html_o, ['p'] = syntax_keywords_html_p, ['r'] = syntax_keywords_html_r, ['s'] = syntax_keywords_html_s, ['t'] = syntax_keywords_html_t, ['u'] = syntax_keywords_html_u, ['v'] = syntax_keywords_html_v, ['w'] = syntax_keywords_html_w
+};
+
diff --git a/keywords.py b/keywords.py
index 951f3b2..c8f7e9c 100755
--- a/keywords.py
+++ b/keywords.py
@@ -216,6 +216,40 @@ builtins_python = ['ArithmeticError', 'AssertionError', 'AttributeError', 'BaseE
     'vars', 'zip',
 ]
 
+attributes_html = [
+	'accept','accept-charset','accesskey','action','align','alt','async',
+	'autocomplete','autofocus','autoplay','bgcolor','border','charset',
+	'checked','cite','class','color','cols','colspan','content',
+	'contenteditable','controls','coords','data','datetime',
+	'default','defer','dir','dirname','disabled','download','draggable',
+	'enctype','for','form','formaction','headers','height','hidden','high',
+	'href','hreflang','http-equiv','id','ismap','kind','label','lang','list',
+	'loop','low','max','maxlength','media','method','min','multiple','muted',
+	'name','novalidate','onabort','onafterprint','onbeforeprint',
+	'onbeforeunload','onblur','oncanplay','oncanplaythrough','onchange',
+	'onclick','oncontextmenu','oncopy','oncuechange','oncut','ondblclick',
+	'ondrag','ondragend','ondragenter','ondragleave','ondragover','ondragstart',
+	'ondrop','ondurationchange','onemptied','onended','onerror','onfocus',
+	'onhashchange','oninput','oninvalid','onkeydown','onkeypress','onkeyup',
+	'onload','onloadeddata','onloadedmetadata','onloadstart','onmousedown',
+	'onmousemove','onmouseout','onmouseover','onmouseup','onmousewheel','onoffline',
+	'ononline','onpagehide','onpageshow','onpaste','onpause','onplay','onplaying',
+	'onpopstate','onprogress','onratechange','onreset','onresize','onscroll',
+	'onsearch','onseeked','onseeking','onselect','onstalled','onstorage',
+	'onsubmit','onsuspend','ontimeupdate','ontoggle','onunload','onvolumechange',
+	'onwaiting','onwheel','open','optimum','pattern','placeholder','poster',
+	'preload','readonly','rel','required','reversed','rows','rowspan','sandbox',
+	'scope','selected','shape','size','sizes','span','spellcheck','src','srcdoc',
+	'srclang','srcset','start','step','style','tabindex','target',
+	'title','translate','type','usemap','value','width','wrap'
+]
+
+assert len(attributes_html) == len(set(attributes_html))
+
+builtins_html = []
+for attr in attributes_html:
+	builtins_html.append(attr + '=')
+
 file = open('keywords.h', 'w')
 file.write('''// keywords for all languages ted supports
 // This file was auto-generated by keywords.py
@@ -239,4 +273,5 @@ cpp_things.remove((SYNTAX_BUILTIN, 'wchar_t'))
 output_keywords(file, cpp_things, 'cpp')
 output_keywords(file, label(keywords_rust, SYNTAX_KEYWORD) + label(builtins_rust, SYNTAX_BUILTIN) + label(constants_rust, SYNTAX_CONSTANT), 'rust')
 output_keywords(file, label(keywords_python, SYNTAX_KEYWORD) + label(builtins_python, SYNTAX_BUILTIN), 'python')
+output_keywords(file, label(builtins_html, SYNTAX_BUILTIN), 'html')
 file.close()
diff --git a/main.c b/main.c
index 64fc96d..044a11b 100644
--- a/main.c
+++ b/main.c
@@ -1,4 +1,7 @@
-// HTML highlighting
+// Highlighting for:
+// - Config (cfg)
+// :set-language command; -1 = default language for this extension
+
 #include "base.h"
 no_warn_start
 #if _WIN32
diff --git a/syntax.c b/syntax.c
index 0a4805d..2e361cf 100644
--- a/syntax.c
+++ b/syntax.c
@@ -21,6 +21,7 @@ char const *language_comment_start(Language l) {
 	case LANG_CPP: return "// ";
 	case LANG_PYTHON: return "# ";
 	case LANG_TEX: return "% ";
+	case LANG_HTML: return "<!-- ";
 	case LANG_NONE:
 	case LANG_MARKDOWN:
 	case LANG_COUNT:
@@ -34,6 +35,8 @@ char const *language_comment_end(Language l) {
 	switch (l) {
 	case LANG_C:
 		return " */";
+	case LANG_HTML:
+		return " -->";
 	default:
 		return "";
 	}
@@ -54,10 +57,10 @@ ColorSetting syntax_char_type_to_color(SyntaxCharType t) {
 	return COLOR_TEXT;
 }
 
-static inline bool syntax_keyword_matches(char32_t *text, size_t len, char const *keyword) {
+static inline bool syntax_keyword_matches(char32_t const *text, size_t len, char const *keyword) {
 	if (len == strlen(keyword)) {
 		bool matches = true;
-		char32_t *p = text;
+		char32_t const *p = text;
 		// check if `p` starts with `keyword`
 		for (char const *q = keyword; *q; ++p, ++q) {
 			if (*p != (char32_t)*q) {
@@ -98,7 +101,7 @@ bool syntax_is_opening_bracket(Language lang, char32_t c) {
 }
 
 // lookup the given string in the keywords table
-static Keyword const *syntax_keyword_lookup(Keyword const *const *all_keywords, size_t n_all_keywords, char32_t *str, size_t len) {
+static Keyword const *syntax_keyword_lookup(Keyword const *const *all_keywords, size_t n_all_keywords, char32_t const *str, size_t len) {
 	if (!len) return NULL;
 	if (str[0] >= n_all_keywords) return NULL;
 
@@ -115,7 +118,7 @@ static Keyword const *syntax_keyword_lookup(Keyword const *const *all_keywords,
 }
 
 // does i continue the number literal from i-1
-static inline bool syntax_number_continues(char32_t *line, u32 line_len, u32 i) {
+static inline bool syntax_number_continues(char32_t const *line, u32 line_len, u32 i) {
 	if (line[i] == '.' && ((i && line[i-1] == '.') || (i < line_len-1 && line[i+1] == '.')))
 		return false; // can't have two .s in a row
 	return (line[i] < CHAR_MAX && 
@@ -123,19 +126,34 @@ static inline bool syntax_number_continues(char32_t *line, u32 line_len, u32 i)
 		|| (i && line[i-1] == 'e' && (line[i] == '+' || line[i] == '-'))));
 }
 
+static bool is_keyword(Language lang, char32_t c) {
+	if (is32_ident(c)) return true;
+	switch (lang) {
+	case LANG_RUST:
+		// Rust builtin macros
+		if (c == '!')
+			return true;
+		break;
+	case LANG_HTML:
+		if (c == '-' || c == '=')
+			return true;
+		break;
+	default: break;
+	}
+	return false;
+}
+
 // find how long this keyword would be (if this is a keyword)
-static inline u32 syntax_keyword_len(Language lang, char32_t *line, u32 i, u32 line_len) {
+static inline u32 syntax_keyword_len(Language lang, char32_t const *line, u32 i, u32 line_len) {
 	u32 keyword_end;
-	for (keyword_end = i; 
-		keyword_end < line_len 
-		&& (is32_ident(line[keyword_end]) 
-		|| (lang == LANG_RUST && line[keyword_end] == '!')) // for rust builtin macros		
-		; ++keyword_end);
+	for (keyword_end = i; keyword_end < line_len; ++keyword_end) {
+		if (!is_keyword(lang, line[keyword_end]))
+			break;
+	}
 	return keyword_end - i;
 }	
 
-
-static void syntax_highlight_c_cpp(SyntaxState *state_ptr, bool cpp, char32_t *line, u32 line_len, SyntaxCharType *char_types) {
+static void syntax_highlight_c_cpp(SyntaxState *state_ptr, bool cpp, char32_t const *line, u32 line_len, SyntaxCharType *char_types) {
 	SyntaxState state = *state_ptr;
 	bool in_preprocessor = (state & SYNTAX_STATE_CPP_PREPROCESSOR) != 0;
 	bool in_string = (state & SYNTAX_STATE_CPP_STRING) != 0;
@@ -293,7 +311,7 @@ static void syntax_highlight_c_cpp(SyntaxState *state_ptr, bool cpp, char32_t *l
 	);
 }
 
-static void syntax_highlight_rust(SyntaxState *state, char32_t *line, u32 line_len, SyntaxCharType *char_types) {
+static void syntax_highlight_rust(SyntaxState *state, char32_t const *line, u32 line_len, SyntaxCharType *char_types) {
 	u32 comment_depth = (((u32)*state & SYNTAX_STATE_RUST_COMMENT_DEPTH_MASK) / SYNTAX_STATE_RUST_COMMENT_DEPTH_MUL);
 	bool in_string = (*state & SYNTAX_STATE_RUST_STRING) != 0;
 	bool string_is_raw = (*state & SYNTAX_STATE_RUST_STRING_IS_RAW) != 0;
@@ -446,7 +464,7 @@ static void syntax_highlight_rust(SyntaxState *state, char32_t *line, u32 line_l
 	);
 }
 
-static void syntax_highlight_python(SyntaxState *state, char32_t *line, u32 line_len, SyntaxCharType *char_types) {
+static void syntax_highlight_python(SyntaxState *state, char32_t const *line, u32 line_len, SyntaxCharType *char_types) {
 	(void)state;
 	bool in_string = (*state & SYNTAX_STATE_PYTHON_STRING) != 0;
 	bool string_is_dbl_quoted = (*state & SYNTAX_STATE_PYTHON_STRING_DBL_QUOTED) != 0;
@@ -559,7 +577,7 @@ static bool is_tex_ident(char32_t c) {
 	return is32_ident(c) && !is32_digit(c);
 }
 
-static void syntax_highlight_tex(SyntaxState *state, char32_t *line, u32 line_len, SyntaxCharType *char_types) {
+static void syntax_highlight_tex(SyntaxState *state, char32_t const *line, u32 line_len, SyntaxCharType *char_types) {
 	bool dollar = (*state & SYNTAX_STATE_TEX_DOLLAR) != 0;
 	bool dollardollar = (*state & SYNTAX_STATE_TEX_DOLLARDOLLAR) != 0;
 	bool verbatim = (*state & SYNTAX_STATE_TEX_VERBATIM) != 0;
@@ -577,7 +595,7 @@ static void syntax_highlight_tex(SyntaxState *state, char32_t *line, u32 line_le
 					if (is_tex_ident(line[i+1])) {
 						// command, e.g. \begin
 						String32 command_str = {
-							.str = line + i+1,
+							.str = (char32_t *)line + i+1,
 							.len = line_len - (i+1),
 						};
 						bool new_verbatim = false;
@@ -658,7 +676,7 @@ static void syntax_highlight_tex(SyntaxState *state, char32_t *line, u32 line_le
 	);
 }
 
-static void syntax_highlight_markdown(SyntaxState *state, char32_t *line, u32 line_len, SyntaxCharType *char_types) {
+static void syntax_highlight_markdown(SyntaxState *state, char32_t const *line, u32 line_len, SyntaxCharType *char_types) {
 	bool multiline_code = (*state & SYNTAX_STATE_MARKDOWN_CODE) != 0;
 	
 	*state = (multiline_code * SYNTAX_STATE_MARKDOWN_CODE);
@@ -703,7 +721,7 @@ static void syntax_highlight_markdown(SyntaxState *state, char32_t *line, u32 li
 		}
 		
 		String32 remains = {
-			.str = line + i,
+			.str = (char32_t *)line + i,
 			.len = line_len - i
 		};
 		if (!format_ending && str32_has_ascii_prefix(remains, "http")) {
@@ -845,11 +863,121 @@ static void syntax_highlight_markdown(SyntaxState *state, char32_t *line, u32 li
 	
 }
 
+static bool is_html_tag_char(char32_t c) {
+	return c == '<' || c == '/' || c == '!' || is32_alnum(c);
+}
+
+static void syntax_highlight_html(SyntaxState *state, char32_t const *line, u32 line_len, SyntaxCharType *char_types) {
+	bool comment = (*state & SYNTAX_STATE_HTML_COMMENT) != 0;
+	bool in_sgl_string = false; // 'string'
+	bool in_dbl_string = false; // "string"
+	int backslashes = 0;
+	for (u32 i = 0; i < line_len; ++i) {
+		String32 remains = {
+			.str = (char32_t *)line + i,
+			.len = line_len - i
+		};
+		bool has_1_char = i + 1 < line_len;
+		
+		if (comment) {
+			if (str32_has_ascii_prefix(remains, "-->")) {
+				if (char_types)
+					memset(&char_types[i], SYNTAX_COMMENT, 3);
+				i += 2;
+				// (don't worry, comments can't nest in HTML)
+				comment = false;
+			} else {
+				if (char_types) char_types[i] = SYNTAX_COMMENT;
+			}
+		} else if (!in_sgl_string && !in_dbl_string && str32_has_ascii_prefix(remains, "<!--")) {
+			comment = true;
+			if (char_types) char_types[i] = SYNTAX_COMMENT;
+		} else if (in_sgl_string || in_dbl_string) {
+			if (char_types)
+				char_types[i] = SYNTAX_STRING;
+			if (line[i] == (in_sgl_string ? '\'' : '"') && backslashes % 2 == 0)
+				in_sgl_string = in_dbl_string = false;
+		} else {
+			if (char_types) char_types[i] = SYNTAX_NORMAL;
+			switch (line[i]) {
+			case '"':
+				if (i > 0 && line[i-1] == '=') {
+					in_dbl_string = true;
+					if (char_types)
+						char_types[i] = SYNTAX_STRING;
+				}
+				break;
+			case '\'':
+				if (i > 0 && line[i-1] == '=') {
+					in_sgl_string = true;
+					if (char_types)
+						char_types[i] = SYNTAX_STRING;
+				}
+				break;
+			case '&':
+				for (; i < line_len; ++i) {
+					if (char_types)
+						char_types[i] = SYNTAX_BUILTIN;
+					if (line[i] == ';')
+						break;
+				}
+				break;
+			case '<':
+				if (has_1_char && is_html_tag_char(line[i+1])) {
+					for (; i < line_len; ++i) {
+						if (!is_html_tag_char(line[i])) {
+							--i;
+							break;
+						}
+						if (char_types)
+							char_types[i] = SYNTAX_KEYWORD;
+					}
+				}
+				break;
+			case '>':
+				if (char_types) {
+					// we want to check if the character before it is a space so that
+					// > in JavaScript/PHP doesn't get picked up as a "tag".
+					if (i > 0 && !is32_space(line[i-1])) {
+						char_types[i] = SYNTAX_KEYWORD;
+						if (line[i-1] == '/') // tags like <thing+ />
+							char_types[i-1] = SYNTAX_KEYWORD;
+					}
+				}
+				break;
+			default:
+				if (char_types) {
+					u32 keyword_len = syntax_keyword_len(LANG_HTML, line, i, line_len);
+					Keyword const *keyword = syntax_keyword_lookup(syntax_all_keywords_html, arr_count(syntax_all_keywords_html),
+						&line[i], keyword_len);
+					if (keyword) {
+						SyntaxCharType type = keyword->type;
+						for (size_t j = 0; j < keyword_len; ++j) {
+							char_types[i++] = type;
+						}
+						--i; // we'll increment i from the for loop
+						break;
+					}
+				}
+				break;
+			}
+		}
+		if (i < line_len) {
+			if (line[i] == '\\')
+				++backslashes;
+			else
+				backslashes = 0;
+		}
+	}
+	
+	*state = (comment * SYNTAX_STATE_HTML_COMMENT);
+}
+
 // This is the main syntax highlighting function. It will determine which colors to use for each character.
 // Rather than returning colors, it returns a character type (e.g. comment) which can be converted to a color.
 // To highlight multiple lines, start out with a zeroed SyntaxState, and pass a pointer to it each time.
 // You can set char_types to NULL if you just want to advance the state, and don't care about the character types.
-void syntax_highlight(SyntaxState *state, Language lang, char32_t *line, u32 line_len, SyntaxCharType *char_types) {
+void syntax_highlight(SyntaxState *state, Language lang, char32_t const *line, u32 line_len, SyntaxCharType *char_types) {
 	switch (lang) {
 	case LANG_NONE:
 		if (char_types)
@@ -873,6 +1001,9 @@ void syntax_highlight(SyntaxState *state, Language lang, char32_t *line, u32 lin
 	case LANG_MARKDOWN:
 		syntax_highlight_markdown(state, line, line_len, char_types);
 		break;
+	case LANG_HTML:
+		syntax_highlight_html(state, line, line_len, char_types);
+		break;
 	case LANG_COUNT: assert(0); break;
 	}
 }
diff --git a/ted.cfg b/ted.cfg
index 1ed74cc..aa15520 100644
--- a/ted.cfg
+++ b/ted.cfg
@@ -203,9 +203,10 @@ cursor-line-number = #ddf
 line-numbers-separator = #fff3
 
 [extensions]
-C = .c, .h
+C = .c, .h, .glsl
 C++ = .cpp, .hpp, .C, .H, .cxx, .hxx, .cc, .hh
 Rust = .rs
 Python = .py
 Tex = .tex
 Markdown = .md 
+HTML = .html, .php
diff --git a/ted.h b/ted.h
index c05f8d3..6e61ea9 100644
--- a/ted.h
+++ b/ted.h
@@ -37,6 +37,10 @@ enum {
 	SYNTAX_STATE_MARKDOWN_CODE = 0x01u, // inside ``` ``` code section
 };
 
+enum {
+	SYNTAX_STATE_HTML_COMMENT = 0x01u
+};
+
 typedef u8 SyntaxState;
 
 ENUM_U16 {
@@ -47,6 +51,7 @@ ENUM_U16 {
 	LANG_PYTHON,
 	LANG_TEX,
 	LANG_MARKDOWN,
+	LANG_HTML,
 	LANG_COUNT
 } ENUM_U16_END(Language);
 
@@ -63,6 +68,7 @@ static LanguageName const language_names[] = {
 	{LANG_PYTHON, "Python"},
 	{LANG_TEX, "Tex"},
 	{LANG_MARKDOWN, "Markdown"},
+	{LANG_HTML, "HTML"},
 };
 
 static_assert_if_possible(arr_count(language_names) == LANG_COUNT)