Update gen_tags.py to exempt generated files from clang-format, and r…

…egen the tag lists.

gentags.py

@@ -1,10 +1,17 @@
 import sys
 
-tag_strings = open("src/tag_strings.h", "w")
-tag_enum = open("src/tag_enum.h", "w")
-tag_sizes = open("src/tag_sizes.h", "w")
+def open_and_write_header(filename, comment_prefix):
+  f = open(filename, 'w')
+  f.write(comment_prefix + ' Generated via `gentags.py src/tag.in`.\n')
+  f.write(comment_prefix + ' Do not edit; edit src/tag.in instead.\n')
+  f.write(comment_prefix + ' clang-format off\n')
+  return f
 
-tag_py = open("python/gumbo/gumboc_tags.py", "w")
+tag_strings = open_and_write_header('src/tag_strings.h', '//')
+tag_enum = open_and_write_header('src/tag_enum.h', '//')
+tag_sizes = open_and_write_header('src/tag_sizes.h', '//')
+
+tag_py = open_and_write_header('python/gumbo/gumboc_tags.py', '#')
 tag_py.write('TagNames = [\n')
 
 tagfile = open(sys.argv[1])
@@ -15,7 +22,7 @@
     tag_strings.write('"%s",\n' % tag)
     tag_enum.write('GUMBO_TAG_%s,\n' % tag_upper)
     tag_sizes.write('%d, ' % len(tag))
-    tag_py.write('\t"%s",\n' % tag_upper)
+    tag_py.write('  "%s",\n' % tag_upper)
 
 tagfile.close()
 

python/gumbo/gumboc_tags.py

@@ -1,152 +1,155 @@
+# Generated via `gentags.py src/tag.in`.
+# Do not edit; edit src/tag.in instead.
+# clang-format off
 TagNames = [
-	"HTML",
-	"HEAD",
-	"TITLE",
-	"BASE",
-	"LINK",
-	"META",
-	"STYLE",
-	"SCRIPT",
-	"NOSCRIPT",
-	"TEMPLATE",
-	"BODY",
-	"ARTICLE",
-	"SECTION",
-	"NAV",
-	"ASIDE",
-	"H1",
-	"H2",
-	"H3",
-	"H4",
-	"H5",
-	"H6",
-	"HGROUP",
-	"HEADER",
-	"FOOTER",
-	"ADDRESS",
-	"P",
-	"HR",
-	"PRE",
-	"BLOCKQUOTE",
-	"OL",
-	"UL",
-	"LI",
-	"DL",
-	"DT",
-	"DD",
-	"FIGURE",
-	"FIGCAPTION",
-	"MAIN",
-	"DIV",
-	"A",
-	"EM",
-	"STRONG",
-	"SMALL",
-	"S",
-	"CITE",
-	"Q",
-	"DFN",
-	"ABBR",
-	"DATA",
-	"TIME",
-	"CODE",
-	"VAR",
-	"SAMP",
-	"KBD",
-	"SUB",
-	"SUP",
-	"I",
-	"B",
-	"U",
-	"MARK",
-	"RUBY",
-	"RT",
-	"RP",
-	"BDI",
-	"BDO",
-	"SPAN",
-	"BR",
-	"WBR",
-	"INS",
-	"DEL",
-	"IMAGE",
-	"IMG",
-	"IFRAME",
-	"EMBED",
-	"OBJECT",
-	"PARAM",
-	"VIDEO",
-	"AUDIO",
-	"SOURCE",
-	"TRACK",
-	"CANVAS",
-	"MAP",
-	"AREA",
-	"MATH",
-	"MI",
-	"MO",
-	"MN",
-	"MS",
-	"MTEXT",
-	"MGLYPH",
-	"MALIGNMARK",
-	"ANNOTATION_XML",
-	"SVG",
-	"FOREIGNOBJECT",
-	"DESC",
-	"TABLE",
-	"CAPTION",
-	"COLGROUP",
-	"COL",
-	"TBODY",
-	"THEAD",
-	"TFOOT",
-	"TR",
-	"TD",
-	"TH",
-	"FORM",
-	"FIELDSET",
-	"LEGEND",
-	"LABEL",
-	"INPUT",
-	"BUTTON",
-	"SELECT",
-	"DATALIST",
-	"OPTGROUP",
-	"OPTION",
-	"TEXTAREA",
-	"KEYGEN",
-	"OUTPUT",
-	"PROGRESS",
-	"METER",
-	"DETAILS",
-	"SUMMARY",
-	"MENU",
-	"MENUITEM",
-	"APPLET",
-	"ACRONYM",
-	"BGSOUND",
-	"DIR",
-	"FRAME",
-	"FRAMESET",
-	"NOFRAMES",
-	"ISINDEX",
-	"LISTING",
-	"XMP",
-	"NEXTID",
-	"NOEMBED",
-	"PLAINTEXT",
-	"RB",
-	"STRIKE",
-	"BASEFONT",
-	"BIG",
-	"BLINK",
-	"CENTER",
-	"FONT",
-	"MARQUEE",
-	"MULTICOL",
-	"NOBR",
-	"SPACER",
-	"TT",
-	"RTC",
+  "HTML",
+  "HEAD",
+  "TITLE",
+  "BASE",
+  "LINK",
+  "META",
+  "STYLE",
+  "SCRIPT",
+  "NOSCRIPT",
+  "TEMPLATE",
+  "BODY",
+  "ARTICLE",
+  "SECTION",
+  "NAV",
+  "ASIDE",
+  "H1",
+  "H2",
+  "H3",
+  "H4",
+  "H5",
+  "H6",
+  "HGROUP",
+  "HEADER",
+  "FOOTER",
+  "ADDRESS",
+  "P",
+  "HR",
+  "PRE",
+  "BLOCKQUOTE",
+  "OL",
+  "UL",
+  "LI",
+  "DL",
+  "DT",
+  "DD",
+  "FIGURE",
+  "FIGCAPTION",
+  "MAIN",
+  "DIV",
+  "A",
+  "EM",
+  "STRONG",
+  "SMALL",
+  "S",
+  "CITE",
+  "Q",
+  "DFN",
+  "ABBR",
+  "DATA",
+  "TIME",
+  "CODE",
+  "VAR",
+  "SAMP",
+  "KBD",
+  "SUB",
+  "SUP",
+  "I",
+  "B",
+  "U",
+  "MARK",
+  "RUBY",
+  "RT",
+  "RP",
+  "BDI",
+  "BDO",
+  "SPAN",
+  "BR",
+  "WBR",
+  "INS",
+  "DEL",
+  "IMAGE",
+  "IMG",
+  "IFRAME",
+  "EMBED",
+  "OBJECT",
+  "PARAM",
+  "VIDEO",
+  "AUDIO",
+  "SOURCE",
+  "TRACK",
+  "CANVAS",
+  "MAP",
+  "AREA",
+  "MATH",
+  "MI",
+  "MO",
+  "MN",
+  "MS",
+  "MTEXT",
+  "MGLYPH",
+  "MALIGNMARK",
+  "ANNOTATION_XML",
+  "SVG",
+  "FOREIGNOBJECT",
+  "DESC",
+  "TABLE",
+  "CAPTION",
+  "COLGROUP",
+  "COL",
+  "TBODY",
+  "THEAD",
+  "TFOOT",
+  "TR",
+  "TD",
+  "TH",
+  "FORM",
+  "FIELDSET",
+  "LEGEND",
+  "LABEL",
+  "INPUT",
+  "BUTTON",
+  "SELECT",
+  "DATALIST",
+  "OPTGROUP",
+  "OPTION",
+  "TEXTAREA",
+  "KEYGEN",
+  "OUTPUT",
+  "PROGRESS",
+  "METER",
+  "DETAILS",
+  "SUMMARY",
+  "MENU",
+  "MENUITEM",
+  "APPLET",
+  "ACRONYM",
+  "BGSOUND",
+  "DIR",
+  "FRAME",
+  "FRAMESET",
+  "NOFRAMES",
+  "ISINDEX",
+  "LISTING",
+  "XMP",
+  "NEXTID",
+  "NOEMBED",
+  "PLAINTEXT",
+  "RB",
+  "STRIKE",
+  "BASEFONT",
+  "BIG",
+  "BLINK",
+  "CENTER",
+  "FONT",
+  "MARQUEE",
+  "MULTICOL",
+  "NOBR",
+  "SPACER",
+  "TT",
+  "RTC",
 ]

src/tag_enum.h

@@ -1,3 +1,6 @@
+// Generated via `gentags.py src/tag.in`.
+// Do not edit; edit src/tag.in instead.
+// clang-format off
 GUMBO_TAG_HTML,
 GUMBO_TAG_HEAD,
 GUMBO_TAG_TITLE,

src/tag_sizes.h

@@ -1 +1,4 @@
+// Generated via `gentags.py src/tag.in`.
+// Do not edit; edit src/tag.in instead.
+// clang-format off
 4, 4, 5, 4, 4, 4, 5, 6, 8, 8, 4, 7, 7, 3, 5, 2, 2, 2, 2, 2, 2, 6, 6, 6, 7, 1, 2, 3, 10, 2, 2, 2, 2, 2, 2, 6, 10, 4, 3, 1, 2, 6, 5, 1, 4, 1, 3, 4, 4, 4, 4, 3, 4, 3, 3, 3, 1, 1, 1, 4, 4, 2, 2, 3, 3, 4, 2, 3, 3, 3, 5, 3, 6, 5, 6, 5, 5, 5, 6, 5, 6, 3, 4, 4, 2, 2, 2, 2, 5, 6, 10, 14, 3, 13, 4, 5, 7, 8, 3, 5, 5, 5, 2, 2, 2, 4, 8, 6, 5, 5, 6, 6, 8, 8, 6, 8, 6, 6, 8, 5, 7, 7, 4, 8, 6, 7, 7, 3, 5, 8, 8, 7, 7, 3, 6, 7, 9, 2, 6, 8, 3, 5, 6, 4, 7, 8, 4, 6, 2, 3, 

src/tag_strings.h

@@ -1,3 +1,6 @@
+// Generated via `gentags.py src/tag.in`.
+// Do not edit; edit src/tag.in instead.
+// clang-format off
 "html",
 "head",
 "title",