@jdeighan/coffee-utils 14.0.31 → 14.0.33

package/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "@jdeighan/coffee-utils",
 	"type": "module",
-	"version": "14.0.31",
+	"version": "14.0.33",
 	"description": "A set of utility functions for CoffeeScript",
 	"main": "coffee_utils.js",
 	"exports": {
@@ -45,14 +45,14 @@
 	},
 	"homepage": "https://github.com/johndeighan/coffee-utils#readme",
 	"dependencies": {
-		"@jdeighan/base-utils": "^4.0.15",
+		"@jdeighan/base-utils": "^4.0.19",
 		"cross-env": "^7.0.3",
 		"n-readlines": "^1.0.1",
 		"readline-sync": "^1.4.10",
 		"svelte": "^3.55.1"
 	},
 	"devDependencies": {
-		"@jdeighan/unit-tester": "^3.0.39",
+		"@jdeighan/unit-tester": "^3.0.41",
 		"ava": "^5.1.1"
 	}
 }

package/src/html.coffee

@@ -2,8 +2,9 @@
 
 import {assert, croak} from '@jdeighan/base-utils/exceptions'
 import {
-	undef, pass, words, isEmpty, nonEmpty, toBlock,
+	undef, pass, words, isEmpty, nonEmpty, toBlock, OL, getOptions,
 	} from '@jdeighan/base-utils'
+import {dbgEnter, dbgReturn, dbg} from '@jdeighan/base-utils/debug'
 import {indented} from '@jdeighan/coffee-utils/indent'
 
 hNoEnd = {}
@@ -211,3 +212,58 @@ export elem = (tagName, hAttr=undef, text=undef, oneIndent="\t") =>
 			indented(text, 1, oneIndent)
 			tag2str(hToken, 'end')
 			])
+
+# ---------------------------------------------------------------------------
+
+export formatHTML = (html, hOptions={}) =>
+
+	dbgEnter 'formatHTML', html, hOptions
+	{oneIndent} = getOptions(hOptions, {
+		oneIndent: '   '
+		})
+
+	html = html.trim()    # remove any leading/trailing whitespace
+	assert html.charAt(0) == '<', "Bad HTML, no < at start"
+	assert html.charAt(html.length-1) == '>', "Bad HTML, no > at end"
+
+	# --- Remove leading '<' and trailing '>'
+	html = html.substring(1, html.length-1)
+
+	hNoEndTag = {}
+	for tag in words("""
+			br hr img input link base
+			meta param area embed
+			col track source
+			""")
+		hNoEndTag[tag] = true
+
+	lParts = []
+	level = 0
+
+	for elem in html.split(/>\s*</)
+		dbg "ELEM: #{OL(elem)}"
+		[_, endMarker, tagName, rest] = elem.match(///^
+			(\/)?                     # possible end tag
+			([A-Za-z][A-Za-z0-9-]*)   # tag name
+			(.*)                      # everything else
+			$///)
+		if endMarker
+			dbg "   TAG: #{OL(tagName)} - END MARKER"
+		else
+			dbg "   TAG: #{OL(tagName)} - NO END MARKER"
+
+		if endMarker && (level > 0)
+			# --- If end tag, reduce level
+			dbg "   reduce level #{level} to #{level-1}"
+			level -= 1
+
+		dbg "   ADD #{OL(elem)} at level #{level}"
+		lParts.push oneIndent.repeat(level), "<#{elem}>\n"
+
+		if ! endMarker && ! hNoEndTag[tagName] && !rest.endsWith('/'+tagName)
+			dbg "   inc level #{level} to #{level+1}"
+			level += 1
+
+	result = lParts.join('').trim()
+	dbgReturn 'formatHTML', result
+	return result

package/src/html.js

@@ -13,9 +13,17 @@ import {
   words,
   isEmpty,
   nonEmpty,
-  toBlock
+  toBlock,
+  OL,
+  getOptions
 } from '@jdeighan/base-utils';
 
+import {
+  dbgEnter,
+  dbgReturn,
+  dbg
+} from '@jdeighan/base-utils/debug';
+
 import {
   indented
 } from '@jdeighan/coffee-utils/indent';
@@ -214,3 +222,54 @@ export var elem = (tagName, hAttr = undef, text = undef, oneIndent = "\t") => {
     return toBlock([tag2str(hToken, 'begin'), indented(text, 1, oneIndent), tag2str(hToken, 'end')]);
   }
 };
+
+// ---------------------------------------------------------------------------
+export var formatHTML = (html, hOptions = {}) => {
+  var _, endMarker, hNoEndTag, j, k, lParts, len1, len2, level, oneIndent, ref1, ref2, rest, result, tag;
+  dbgEnter('formatHTML', html, hOptions);
+  ({oneIndent} = getOptions(hOptions, {
+    oneIndent: '   '
+  }));
+  html = html.trim(); // remove any leading/trailing whitespace
+  assert(html.charAt(0) === '<', "Bad HTML, no < at start");
+  assert(html.charAt(html.length - 1) === '>', "Bad HTML, no > at end");
+  // --- Remove leading '<' and trailing '>'
+  html = html.substring(1, html.length - 1);
+  hNoEndTag = {};
+  ref1 = words(`br hr img input link base
+meta param area embed
+col track source`);
+  for (j = 0, len1 = ref1.length; j < len1; j++) {
+    tag = ref1[j];
+    hNoEndTag[tag] = true;
+  }
+  lParts = [];
+  level = 0;
+  ref2 = html.split(/>\s*</);
+  for (k = 0, len2 = ref2.length; k < len2; k++) {
+    elem = ref2[k];
+    dbg(`ELEM: ${OL(elem)}`);
+    [_, endMarker, tagName, rest] = elem.match(/^(\/)?([A-Za-z][A-Za-z0-9-]*)(.*)$/); // possible end tag
+    // tag name
+    // everything else
+    if (endMarker) {
+      dbg(`   TAG: ${OL(tagName)} - END MARKER`);
+    } else {
+      dbg(`   TAG: ${OL(tagName)} - NO END MARKER`);
+    }
+    if (endMarker && (level > 0)) {
+      // --- If end tag, reduce level
+      dbg(`   reduce level ${level} to ${level - 1}`);
+      level -= 1;
+    }
+    dbg(`   ADD ${OL(elem)} at level ${level}`);
+    lParts.push(oneIndent.repeat(level), `<${elem}>\n`);
+    if (!endMarker && !hNoEndTag[tagName] && !rest.endsWith('/' + tagName)) {
+      dbg(`   inc level ${level} to ${level + 1}`);
+      level += 1;
+    }
+  }
+  result = lParts.join('').trim();
+  dbgReturn('formatHTML', result);
+  return result;
+};