feat(formatter): will now attempt to fix case on known html tags by d…

…efault, can be disabled

closes #589

docs/src/_data/configuration.json

@@ -435,5 +435,24 @@
         "value": "\"files\": [\n        \"index.html\"\n    }"
       }
     ]
+  },
+  {
+    "name": "ignore_case",
+    "tags": ["formatter"],
+    "description": {
+      "en": "Do not attempt to fix the case of known html tags.",
+      "ru": "Не пытайтесь исправить регистр известных html-тегов.",
+      "fr": "N'essayez pas de corriger la casse des balises html connues."
+    },
+    "usage": [
+      {
+        "name": "pyproject.toml",
+        "value": "[tool.djlint]\nignore-case=true\n"
+      },
+      {
+        "name": ".djlintrc",
+        "value": "\"ignore_case\": true"
+      }
+    ]
   }
 ]

docs/src/docs/getting-started.md

@@ -33,6 +33,7 @@ Options:
   --version                 Show the version and exit.
   -e, --extension TEXT      File extension to check [default: html]
   -i, --ignore TEXT         Codes to ignore. ex: "H014,H017"
+  --include TEXT            Codes to include. ex: "H014,H017"
   --reformat                Reformat the file(s).
   --check                   Check formatting on the file(s).
   --indent INTEGER          Indent spacing. [default: 4]
@@ -52,6 +53,7 @@ Options:
   --configuration PATH      Path to global configuration file in .djlintrc format
   --statistics              Count the number of occurrences of each
                             error/warning code.
+  --ignore-case             Do not fix case on known html tags.
   -h, --help                Show this message and exit.
 ```
 

docs/src/fr/docs/getting-started.md

@@ -33,6 +33,7 @@ Options:
   --version                 Show the version and exit.
   -e, --extension TEXT      File extension to check [default: html]
   -i, --ignore TEXT         Codes to ignore. ex: "H014,H017"
+  --include TEXT            Codes to include. ex: "H014,H017"
   --reformat                Reformat the file(s).
   --check                   Check formatting on the file(s).
   --indent INTEGER          Indent spacing. [default: 4]
@@ -52,6 +53,7 @@ Options:
   --configuration PATH      Path to global configuration file in .djlintrc format
   --statistics              Count the number of occurrences of each
                             error/warning code.
+  --ignore-case             Do not fix case on known html tags.
   -h, --help                Show this message and exit.
 ```
 

docs/src/ru/docs/getting-started.md

@@ -33,6 +33,7 @@ Options:
   --version                 Show the version and exit.
   -e, --extension TEXT      File extension to check [default: html]
   -i, --ignore TEXT         Codes to ignore. ex: "H014,H017"
+  --include TEXT            Codes to include. ex: "H014,H017"
   --reformat                Reformat the file(s).
   --check                   Check formatting on the file(s).
   --indent INTEGER          Indent spacing. [default: 4]
@@ -52,6 +53,7 @@ Options:
   --configuration PATH      Path to global configuration file in .djlintrc format
   --statistics              Count the number of occurrences of each
                             error/warning code.
+  --ignore-case             Do not fix case on known html tags.
   -h, --help                Show this message and exit.
 ```
 

src/djlint/__init__.py

@@ -134,6 +134,11 @@
     help='Codes to include. ex: "H014,H017"',
     show_default=False,
 )
+@click.option(
+    "--ignore-case",
+    is_flag=True,
+    help="Do not fix case on known html tags.",
+)
 @colorama_text(autoreset=True)
 def main(
     src: List[str],
@@ -155,6 +160,7 @@ def main(
     configuration: Optional[str],
     statistics: bool,
     include: str,
+    ignore_case: bool,
 ) -> None:
     """djLint · HTML template linter and formatter."""
     config = Config(
@@ -177,6 +183,7 @@ def main(
         configuration=configuration,
         statistics=statistics,
         include=include,
+        ignore_case=ignore_case,
     )
 
     temp_file = None

src/djlint/formatter/compress.py

@@ -4,6 +4,7 @@
 """
 
 import regex as re
+from HtmlTagNames import html_tag_names
 
 from ..helpers import child_of_ignored_block
 from ..settings import Config
@@ -12,6 +13,11 @@
 def compress_html(html: str, config: Config) -> str:
     """Compress html."""
 
+    def _fix_case(tag):
+        if config.ignore_case is False and tag.lower() in html_tag_names:
+            return tag.lower()
+        return tag
+
     def _flatten_attributes(match: re.Match) -> str:
         """Flatten multiline attributes back to one line.
 
@@ -28,65 +34,79 @@ def _flatten_attributes(match: re.Match) -> str:
         close = match.group(3) if "/" not in match.group(3) else f" {match.group(3)}"
 
         # pylint: disable=C0209
-        return "{} {}{}".format(
-            match.group(1),
+        return "<{} {}{}".format(
+            _fix_case(match.group(1)),
             " ".join(x.strip() for x in match.group(2).strip().splitlines()),
             close,
         )
 
     # put attributes on one line
     html = re.sub(
         re.compile(
-            rf"(<(?:{config.indent_html_tags}))\s((?:\s*?(?:\"[^\"]*\"|'[^']*'|{{{{(?:(?!}}}}).)*}}}}|{{%(?:(?!%}}).)*%}}|[^'\">{{}}\/\s]))+)\s*?(/?>)",
+            rf"<({config.indent_html_tags})\s((?:\s*?(?:\"[^\"]*\"|'[^']*'|{{{{(?:(?!}}}}).)*}}}}|{{%(?:(?!%}}).)*%}}|[^'\">{{}}\/\s]))+)\s*?(/?>)",
             flags=re.IGNORECASE | re.MULTILINE | re.VERBOSE,
         ),
         _flatten_attributes,
         html,
     )
 
+    def _closing_clean_space(match):
+        return f"</{_fix_case(match.group(1))}>"
+
     # put closing tags back on one line
     # <a ...
     #     >
     html = re.sub(
         re.compile(
-            rf"(</(?:{config.indent_html_tags}))\s*?(>)",
+            rf"</({config.indent_html_tags})\s*?>",
             flags=re.IGNORECASE | re.MULTILINE | re.VERBOSE,
         ),
-        r"\1\2",
+        _closing_clean_space,
         html,
     )
 
+    def _emtpy_clean_space(match):
+        return f"<{_fix_case(match.group(1))}>"
+
     # remove extra space from empty tags
     # <a >
     #   ^
     html = re.sub(
         re.compile(
-            rf"(<(?:{config.indent_html_tags}))\s*?(>)",
+            rf"<({config.indent_html_tags})\s*?>",
             flags=re.IGNORECASE | re.MULTILINE | re.VERBOSE,
         ),
-        r"\1\2",
+        _emtpy_clean_space,
         html,
     )
 
+    def _void_clean_space(match):
+        return f"<{_fix_case(match.group(1))} />"
+
     # ensure space before closing tag
     # <a />
     #   ^
     html = re.sub(
         re.compile(
-            rf"(<(?:{config.indent_html_tags}))\s*?(/>)",
+            rf"<({config.indent_html_tags})\s*?/>",
             flags=re.IGNORECASE | re.MULTILINE | re.VERBOSE,
         ),
-        r"\1 \2",
+        _void_clean_space,
         html,
     )
 
+    def _doctype_clean_space(match):
+        if config.ignore_case is False:
+            return f"<!DOCTYPE {match.group(2)}>"
+        return f"<!{match.group(1)} {match.group(2)}>"
+
     # cleanup whitespace in doctype
     html = re.sub(
         re.compile(
-            r"(<!(?:doctype))\s((?:\s*?(?:\"[^\"]*\"|'[^']*'|{{(?:(?!}}).)*}}|{%(?:(?!%}).)*%}|[^'\">{}\/\s]))+)\s*?(>)",
+            r"<!(doctype)\s((?:\s*?(?:\"[^\"]*\"|'[^']*'|{{(?:(?!}}).)*}}|{%(?:(?!%}).)*%}|[^'\">{}\/\s]))+)\s*?>",
             flags=re.IGNORECASE | re.MULTILINE | re.VERBOSE,
         ),
-        r"\1 \2\3",
+        _doctype_clean_space,
         html,
     )
 

src/djlint/settings.py

@@ -219,6 +219,7 @@ def __init__(
         configuration: Optional[str] = None,
         statistics: bool = False,
         include: Optional[str] = None,
+        ignore_case: bool = False,
     ):
         self.reformat = reformat
         self.check = check
@@ -273,6 +274,10 @@ def __init__(
 
         self.format_css: bool = format_css or djlint_settings.get("format_css", False)
 
+        self.ignore_case: bool = ignore_case or djlint_settings.get(
+            "ignore_case", False
+        )
+
         # ignore is based on input and also profile
         self.ignore: str = str(ignore or djlint_settings.get("ignore", ""))
         self.include: str = str(include or djlint_settings.get("include", ""))

tests/test_html/test_basics.py

@@ -46,7 +46,7 @@
             "</html>\n"
         ),
         (
-            "<!doctype html>\n"
+            "<!DOCTYPE html>\n"
             "<html>\n"
             "    <head></head>\n"
             "    <body></body>\n"
@@ -315,7 +315,7 @@
             "</html>\n"
         ),
         (
-            "<!doctype html>\n"
+            "<!DOCTYPE html>\n"
             '<html class="no-js" lang="">\n'
             "    <head>\n"
             '        <meta charset="utf-8">\n'
@@ -575,7 +575,7 @@
             "    <foo:bar>\n"
             "    <div>looooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooog block</div>\n"
             "    <div>block</div>\n"
-            "    <DIV>BLOCK</DIV>\n"
+            "    <div>BLOCK</div>\n"
             "    <div>block</div>\n"
             "    <div>block</div>\n"
             "    <div>block</div>\n"
@@ -633,7 +633,7 @@
             "    <foo:div>\n"
             "    <div>looooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooog block</div>\n"
             "    <div>block</div>\n"
-            "    <DIV>BLOCK</DIV>\n"
+            "    <div>BLOCK</div>\n"
             "    <div>block</div>\n"
             "    <div>block</div>\n"
             "    <div>block</div>\n"
@@ -691,7 +691,7 @@
             "    <foo:span>\n"
             "    <div>looooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooog block</div>\n"
             "    <div>block</div>\n"
-            "    <DIV>BLOCK</DIV>\n"
+            "    <div>BLOCK</div>\n"
             "    <div>block</div>\n"
             "    <div>\n"
             "        block\n"
@@ -757,9 +757,9 @@
             "    <div>\n"
             "        block\n"
             "    </div>\n"
-            "    <DIV>\n"
+            "    <div>\n"
             "        BLOCK\n"
-            "    </DIV>\n"
+            "    </div>\n"
             "    <div>\n"
             "        block\n"
             "    </div>\n"
@@ -827,9 +827,9 @@
             "        <div>\n"
             "            block\n"
             "        </div>\n"
-            "        <DIV>\n"
+            "        <div>\n"
             "            BLOCK\n"
-            "        </DIV>\n"
+            "        </div>\n"
             "        <div>\n"
             "            block\n"
             "        </div>\n"
@@ -902,10 +902,10 @@
             "<!-- script like -->\n"
             "<with:colon>\n"
             "<style>.a{color:#f00}</style>\n"
-            "<SCRIPT>\n"
+            "<script>\n"
             "  const func = function() { console.log('Hello, there');}\n"
-            "</SCRIPT>\n"
-            "<STYLE>.A{COLOR:#F00}</STYLE>\n"
+            "</script>\n"
+            "<style>.A{COLOR:#F00}</style>\n"
             "<html:script>\n"
             "    const func = function() { console.log('Hello, there');}\n"
             "</html:script>\n"

tests/test_html/test_case.py

@@ -5,6 +5,7 @@
 import pytest
 
 from src.djlint.reformat import formatter
+from src.djlint.settings import Config
 from tests.conftest import printer
 
 test_data = [
@@ -29,25 +30,25 @@
         ),
         (
             "<!DOCTYPE html>\n"
-            '<HTML CLASS="no-js mY-ClAsS">\n'
-            "    <HEAD>\n"
-            '        <META CHARSET="utf-8">\n'
-            "        <TITLE>My tITlE</TITLE>\n"
-            '        <META NAME="description" content="My CoNtEnT">\n'
-            "    </HEAD>\n"
+            '<html CLASS="no-js mY-ClAsS">\n'
+            "    <head>\n"
+            '        <meta CHARSET="utf-8">\n'
+            "        <title>My tITlE</title>\n"
+            '        <meta NAME="description" content="My CoNtEnT">\n'
+            "    </head>\n"
             "    <body>\n"
-            "        <P>\n"
+            "        <p>\n"
             "            Hello world!\n"
-            "            <BR>\n"
+            "            <br>\n"
             "            This is HTML5 Boilerplate.\n"
-            "        </P>\n"
-            "        <SCRIPT>\n"
+            "        </p>\n"
+            "        <script>\n"
             "      window.ga = function () { ga.q.push(arguments) }; ga.q = []; ga.l = +new Date;\n"
             "      ga('create', 'UA-XXXXX-Y', 'auto'); ga('send', 'pageview')\n"
-            "        </SCRIPT>\n"
-            '        <SCRIPT src="https://www.google-analytics.com/analytics.js" ASYNC DEFER></SCRIPT>\n'
+            "        </script>\n"
+            '        <script src="https://www.google-analytics.com/analytics.js" ASYNC DEFER></script>\n'
             "    </body>\n"
-            "</HTML>\n"
+            "</html>\n"
         ),
         id="case",
     )
@@ -60,3 +61,21 @@ def test_base(source, expected, basic_config):
 
     printer(expected, source, output)
     assert expected == output
+
+
+test_data_two = [
+    pytest.param(
+        ("<dIV></Div>\n" "<bR>\n" "<Br />\n" "<MeTa class='asdf' />\n"),
+        ("<dIV></Div>\n" "<bR>\n" "<Br />\n" "<MeTa class='asdf' />\n"),
+        id="preserve_case",
+    )
+]
+
+
+@pytest.mark.parametrize(("source", "expected"), test_data_two)
+def test_base_two(source, expected):
+    config = Config("dummy/source.html", ignore_case=True)
+    output = formatter(config, source)
+
+    printer(expected, source, output)
+    assert expected == output

tests/test_html/test_doctype_declarations.py

@@ -10,12 +10,12 @@
 test_data = [
     pytest.param(
         ("<!DocType htMl>"),
-        ("<!DocType htMl>\n"),
+        ("<!DOCTYPE htMl>\n"),
         id="case",
     ),
     pytest.param(
         ("<!DocType htMl  >"),
-        ("<!DocType htMl>\n"),
+        ("<!DOCTYPE htMl>\n"),
         id="case_2",
     ),
     pytest.param(