Disclaimer

Please do not email me about this project without reading the disclaimer above.

The tidier makes it easier to perform edits on the HTML (Hypertext Markup Language) source with a text editor. It might do thing such as:

• Put 0, 1 or 2 newline characters before and after each tag as appropriate. If there are newline characters or whitespace characters that should not appear before or after a tag, remove them to tighten up. You will probably need to make this table driven since not everyone will agree which tags deserve a new line and blanks lines before or aft. Some tags such as <font> must be left alone other than possibly consolidating whitespace inside, before or aft, into a single newline or space. If you examine the HTML source of this document you are reading, you can see it has been tidied with a crude search/replace script for consistent newline behaviour.

  By default you might make sure every <p>, <br>, <h?>, <tr>, <td>, <dt>, <dd>, <ol>, <ul> and <li> tag starts on a new line with a blank line ahead of it.

• Remove excess blanks lines. No more than one blank line in a row.
• Consistently convert to the desired line end convention, Unix = Lf, or Windows = CrLf or Mac OS (Operating System) 1-9 = Cr.
• Use consistent all lower case tags.
• Remove lead trail blanks on <li>…</li> <dt>…</dt>.
• Avoid lines longer than 60 characters. Break lines at auspicious points — but never in the middle of a quoted string. Avoid reflowing <pre>.
• Sort meta tags in alphabetical order
• Put parameters of <img> in some standard order, probably not alphabetical, e.g. SRC then width, height, border then alt. ditto for other tags with parameters such as font, dt, table etc.
• Generate a new KEYWORDS metatag based on scooping the phrases in h1, h2 and dt tags (avoiding font tags of course). Combine it with the existing KEYWORDS metatag, removing duplicates and putting the phrases in alphabetical order.
• Indent to show structure.
• insert missing </li>, </dt>, </sd>, </h?> etc. tags. Exactly which ones you want should be configurable. So you may also remove unwanted clutter end tags.
• Insert missing type=text/javascript in <script tags.
• replace " with &quot;, & with &amp;, < with &lt; etc. where they occur in the context of ordinary text.
• Convert css tags to old style on request. That way you can have the convenience of composing with css, but broadcast compatible old style tags. Don’t get too carried away, but you might add some user macros too.
• consolidate tags, e.g.
  remove <b></b>
  <b>both</b> <b>bold</b> => <b>both bold</b>..
  Similarly for:
  <font size=+1><font color=red >…</font></font>
  => <font size=+1 color=red>… </font> .
• Convert colour names to hex or vice versa. See the chart of Netscape colour names, e. g. convert <font color=papayawhip> to <font color=#ffefd5> .
• Remove redundant tags that are already handled by CSS (Cascading Style Sheets) styles.
• Convert stray high bit characters to the equivalent alphabetic entity or a numberic entity if there is no alphabetic entity. Convert numeric entities to alphabetic entities where possible. Standardise on either decimal or hex entities. Also permit documents encoded with entities to be converted to UTF-8 encoding without entities.
• A parser such as JavaCC or ANTLR (Another Tool for Language Recognition) might be useful. See parser in the Java glossary.
• Check all IMG statements to ensure the width and height parameters actually match the size of the *.png, *.gif or *.jpg file. If the image file is missing, insert an easily found comment in the HTML. If the size is wrong, correct it, or alternatively, insert the new size information as an easily found comment, so it can be manually corrected later, or left as is if image resizing was actually intended. Invent a comment to put in deliberately resized images to bypass this check.
• Integrate the Compactor so that the user can alternate between efficient and fluffy easy-to-edit forms.
• Provide an option to convert HTML to plain text by stripping out all the tags. There are a few wrinkles to watch out for.
  1. > may occur improperly unpaired with <. In which case treat it as &gt;.
  2. < and > may appear inside quotes inside <..> in which case they should be treated as ordinary characters.
  3. References should optionally be converted to English so they are not lost, e. g. [フレーム] could be rendered as:
     You can read up on the rules [see http://www.cwi.nl/~dik/english/codes/isbn.html] for calculating the expected check digit.
     If you wanted to get really clever you would avoid mentioning the reference if it were already present nearby in plain text, e. g. [フレーム] should be rendered as:
     You can read up on the rules for calculating the expected check digit at www.cwi.nl/~dik/english/code/isbn.html.
  4. You might also optionally render <b>Wow!</b> as *Wow!* .

The HTML editor features of Swing make this a rather trivial project. Some say that MS Front Page does this already. Not so. It mangles your HTML beyond recognition.

I am working on implementing subset of this problem, reflowing and indenting.

---

standard footer