netwerk/streamconv/converters/mozTXTToHTMLConv.h

   1 /* -*- Mode: C; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
   2 /* ***** BEGIN LICENSE BLOCK *****
   3  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
   4  *
   5  * The contents of this file are subject to the Mozilla Public License Version
   6  * 1.1 (the "License"); you may not use this file except in compliance with
   7  * the License. You may obtain a copy of the License at
   8  * http://www.mozilla.org/MPL/
   9  *
  10  * Software distributed under the License is distributed on an "AS IS" basis,
  11  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  12  * for the specific language governing rights and limitations under the
  13  * License.
  14  *
  15  * The Original Code is the Mozilla Text to HTML converter code.
  16  *
  17  * The Initial Developer of the Original Code is
  18  * Ben Bucksch <http://www.bucksch.org>.
  19  * Portions created by the Initial Developer are Copyright (C) 1999, 2000
  20  * the Initial Developer. All Rights Reserved.
  21  *
  22  * Contributor(s):
  23  *
  24  * Alternatively, the contents of this file may be used under the terms of
  25  * either the GNU General Public License Version 2 or later (the "GPL"), or
  26  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  27  * in which case the provisions of the GPL or the LGPL are applicable instead
  28  * of those above. If you wish to allow use of your version of this file only
  29  * under the terms of either the GPL or the LGPL, and not to allow others to
  30  * use your version of this file under the terms of the MPL, indicate your
  31  * decision by deleting the provisions above and replace them with the notice
  32  * and other provisions required by the GPL or the LGPL. If you do not delete
  33  * the provisions above, a recipient may use your version of this file under
  34  * the terms of any one of the MPL, the GPL or the LGPL.
  35  *
  36  * ***** END LICENSE BLOCK ***** */
  37
  38 /**
  39   Description: Currently only functions to enhance plain text with HTML tags. See mozITXTToHTMLConv. Stream conversion is defunct.
  40 */
  41
  42 #ifndef _mozTXTToHTMLConv_h__
  43 #define _mozTXTToHTMLConv_h__
  44
  45 #include "mozITXTToHTMLConv.h"
  46 #include "nsIIOService.h"
  47 #include "nsString.h"
  48 #include "nsCOMPtr.h"
  49
  50
  51 class mozTXTToHTMLConv : public mozITXTToHTMLConv
  52 {
  53
  54
  55 //////////////////////////////////////////////////////////
  56 public:
  57 //////////////////////////////////////////////////////////
  58
  59   mozTXTToHTMLConv();
  60   virtual ~mozTXTToHTMLConv();
  61   NS_DECL_ISUPPORTS
  62
  63   NS_DECL_MOZITXTTOHTMLCONV
  64   NS_DECL_NSIREQUESTOBSERVER
  65   NS_DECL_NSISTREAMLISTENER
  66   NS_DECL_NSISTREAMCONVERTER
  67
  68 /**
  69   see mozITXTToHTMLConv::ScanTXT
  70  */
  71   void ScanTXT(const PRUnichar * aInString, PRInt32 aInStringLength, PRUint32 whattodo, nsString& aOutString);
  72
  73 /**
  74   see mozITXTToHTMLConv::ScanHTML. We will modify aInString potentially...
  75  */
  76   void ScanHTML(nsString& aInString, PRUint32 whattodo, nsString &aOutString);
  77
  78 /**
  79   see mozITXTToHTMLConv::CiteLevelTXT
  80  */
  81   PRInt32 CiteLevelTXT(const PRUnichar * line,PRUint32& logLineStart);
  82
  83
  84 //////////////////////////////////////////////////////////
  85 protected:
  86 //////////////////////////////////////////////////////////
  87   nsCOMPtr<nsIIOService> mIOService; // for performance reasons, cache the netwerk service...
  88 /**
  89   Completes<ul>
  90   <li>Case 1: mailto: "mozilla@bucksch.org" -> "mailto:mozilla@bucksch.org"
  91   <li>Case 2: http:   "www.mozilla.org"     -> "http://www.mozilla.org"
  92   <li>Case 3: ftp:    "ftp.mozilla.org"     -> "ftp://www.mozilla.org"
  93   </ul>
  94   It does no check, if the resulting URL is valid.
  95   @param text (in): abbreviated URL
  96   @param pos (in): position of "@" (case 1) or first "." (case 2 and 3)
  97   @return Completed URL at success and empty string at failure
  98  */
  99   void CompleteAbbreviatedURL(const PRUnichar * aInString, PRInt32 aInLength,
 100                               const PRUint32 pos, nsString& aOutString);
 101
 102
 103 //////////////////////////////////////////////////////////
 104 private:
 105 //////////////////////////////////////////////////////////
 106
 107   enum LIMTYPE
 108   {
 109     LT_IGNORE,     // limitation not checked
 110     LT_DELIMITER,  // not alphanumeric and not rep[0]. End of text is also ok.
 111     LT_ALPHA,      // alpha char
 112     LT_DIGIT
 113   };
 114
 115 /**
 116   @param text (in): the string to search through.<p>
 117          If before = IGNORE,<br>
 118            rep is compared starting at 1. char of text (text[0]),<br>
 119            else starting at 2. char of text (text[1]).
 120          Chars after "after"-delimiter are ignored.
 121   @param rep (in): the string to look for
 122   @param aRepLen (in): the number of bytes in the string to look for
 123   @param before (in): limitation before rep
 124   @param after (in): limitation after rep
 125   @return true, if rep is found and limitation spec is met or rep is empty
 126 */
 127   PRBool ItMatchesDelimited(const PRUnichar * aInString, PRInt32 aInLength,
 128       const PRUnichar * rep, PRInt32 aRepLen, LIMTYPE before, LIMTYPE after);
 129
 130 /**
 131   @param see ItMatchesDelimited
 132   @return Number of ItMatchesDelimited in text
 133 */
 134   PRUint32 NumberOfMatches(const PRUnichar * aInString, PRInt32 aInStringLength,
 135       const PRUnichar* rep, PRInt32 aRepLen, LIMTYPE before, LIMTYPE after);
 136
 137 /**
 138   Currently only changes "<", ">" and "&". All others stay as they are.<p>
 139   "Char" in function name to avoid side effects with nsString(ch)
 140   constructors.
 141   @param ch (in)
 142   @param aStringToAppendto (out) - the string to append the escaped
 143                                    string to.
 144   @param inAttribute (in) - will escape quotes, too (which is
 145                             only needed for attribute values)
 146 */
 147   void EscapeChar(const PRUnichar ch, nsString& aStringToAppendto,
 148                   PRBool inAttribute);
 149
 150 /**
 151   See EscapeChar. Escapes the string in place.
 152 */
 153   void EscapeStr(nsString& aInString, PRBool inAttribute);
 154
 155 /**
 156   Currently only reverts "<", ">" and "&". All others stay as they are.<p>
 157   @param aInString (in) HTML string
 158   @param aStartPos (in) start index into the buffer
 159   @param aLength (in) length of the buffer
 160   @param aOutString (out) unescaped buffer
 161 */
 162   void UnescapeStr(const PRUnichar * aInString, PRInt32 aStartPos,
 163                    PRInt32 aLength, nsString& aOutString);
 164
 165 /**
 166   <em>Note</em>: I use different strategies to pass context between the
 167   functions (full text and pos vs. cutted text and col0, glphyTextLen vs.
 168   replaceBefore/-After). It makes some sense, but is hard to understand
 169   (maintain) :-(.
 170 */
 171
 172 /**
 173   <p><em>Note:</em> replaceBefore + replaceAfter + 1 (for char at pos) chars
 174   in text should be replaced by outputHTML.</p>
 175   <p><em>Note:</em> This function should be able to process a URL on multiple
 176   lines, but currently, ScanForURLs is called for every line, so it can't.</p>
 177   @param text (in): includes possibly a URL
 178   @param pos (in): position in text, where either ":", "." or "@" are found
 179   @param whathasbeendone (in): What the calling ScanTXT did/has to do with the
 180               (not-linkified) text, i.e. usually the "whattodo" parameter.
 181               (Needed to calculate replaceBefore.) NOT what will be done with
 182               the content of the link.
 183   @param outputHTML (out): URL with HTML-a tag
 184   @param replaceBefore (out): Number of chars of URL before pos
 185   @param replaceAfter (out): Number of chars of URL after pos
 186   @return URL found
 187 */
 188   PRBool FindURL(const PRUnichar * aInString, PRInt32 aInLength, const PRUint32 pos,
 189           const PRUint32 whathasbeendone,
 190           nsString& outputHTML, PRInt32& replaceBefore, PRInt32& replaceAfter);
 191
 192   enum modetype {
 193          unknown,
 194          RFC1738,          /* Check, if RFC1738, APPENDIX compliant,
 195                               like "<URL:http://www.mozilla.org>". */
 196          RFC2396E,         /* RFC2396, APPENDIX E allows anglebrackets (like
 197                               "<http://www.mozilla.org>") (without "URL:") or
 198                               quotation marks(like ""http://www.mozilla.org"").
 199                               Also allow email addresses without scheme,
 200                               e.g. "<mozilla@bucksch.org>" */
 201          freetext,         /* assume heading scheme
 202                               with "[a-zA-Z][a-zA-Z0-9+\-\.]*:" like "news:"
 203                               (see RFC2396, Section 3.1).
 204                               Certain characters (see code) or any whitespace
 205                               (including linebreaks) end the URL.
 206                               Other certain (punctation) characters (see code)
 207                               at the end are stripped off. */
 208          abbreviated       /* Similar to freetext, but without scheme, e.g.
 209                               "www.mozilla.org", "ftp.mozilla.org" and
 210                               "mozilla@bucksch.org". */
 211       /* RFC1738 and RFC2396E type URLs may use multiple lines,
 212          whitespace is stripped. Special characters like ")" stay intact.*/
 213   };
 214
 215 /**
 216  * @param text (in), pos (in): see FindURL
 217  * @param check (in): Start must be conform with this mode
 218  * @param start (out): Position in text, where URL (including brackets or
 219  *             similar) starts
 220  * @return |check|-conform start has been found
 221  */
 222   PRBool FindURLStart(const PRUnichar * aInString, PRInt32 aInLength, const PRUint32 pos,
 223                                const modetype check, PRUint32& start);
 224
 225 /**
 226  * @param text (in), pos (in): see FindURL
 227  * @param check (in): End must be conform with this mode
 228  * @param start (in): see FindURLStart
 229  * @param end (out): Similar to |start| param of FindURLStart
 230  * @return |check|-conform end has been found
 231  */
 232   PRBool FindURLEnd(const PRUnichar * aInString, PRInt32 aInStringLength, const PRUint32 pos,
 233            const modetype check, const PRUint32 start, PRUint32& end);
 234
 235 /**
 236  * @param text (in), pos (in), whathasbeendone (in): see FindURL
 237  * @param check (in): Current mode
 238  * @param start (in), end (in): see FindURLEnd
 239  * @param txtURL (out): Guessed (raw) URL.
 240  *             Without whitespace, but not completed.
 241  * @param desc (out): Link as shown to the user, but already escaped.
 242  *             Should be placed between the <a> and </a> tags.
 243  * @param replaceBefore(out), replaceAfter (out): see FindURL
 244  */
 245   void CalculateURLBoundaries(const PRUnichar * aInString, PRInt32 aInStringLength,
 246      const PRUint32 pos, const PRUint32 whathasbeendone,
 247      const modetype check, const PRUint32 start, const PRUint32 end,
 248      nsString& txtURL, nsString& desc,
 249      PRInt32& replaceBefore, PRInt32& replaceAfter);
 250
 251 /**
 252  * @param txtURL (in), desc (in): see CalculateURLBoundaries
 253  * @param outputHTML (out): see FindURL
 254  * @return A valid URL could be found (and creation of HTML successful)
 255  */
 256   PRBool CheckURLAndCreateHTML(
 257        const nsString& txtURL, const nsString& desc, const modetype mode,
 258        nsString& outputHTML);
 259
 260 /**
 261   @param text (in): line of text possibly with tagTXT.<p>
 262               if col0 is true,
 263                 starting with tagTXT<br>
 264               else
 265                 starting one char before tagTXT
 266   @param col0 (in): tagTXT is on the beginning of the line (or paragraph).
 267               open must be 0 then.
 268   @param tagTXT (in): Tag in plaintext to search for, e.g. "*"
 269   @param aTagTxtLen (in): length of tagTXT.
 270   @param tagHTML (in): HTML-Tag to replace tagTXT with,
 271               without "<" and ">", e.g. "strong"
 272   @param attributeHTML (in): HTML-attribute to add to opening tagHTML,
 273               e.g. "class=txt_star"
 274   @param aOutString: string to APPEND the converted html into
 275   @param open (in/out): Number of currently open tags of type tagHTML
 276   @return Conversion succeeded
 277 */
 278   PRBool StructPhraseHit(const PRUnichar * aInString, PRInt32 aInStringLength, PRBool col0,
 279      const PRUnichar* tagTXT,
 280      PRInt32 aTagTxtLen,
 281      const char* tagHTML, const char* attributeHTML,
 282      nsString& aOutputString, PRUint32& openTags);
 283
 284 /**
 285   @param text (in), col0 (in): see GlyphHit
 286   @param tagTXT (in): Smily, see also StructPhraseHit
 287   @param imageName (in): the basename of the file that contains the image for this smilie
 288   @param outputHTML (out): new string containing the html for the smily
 289   @param glyphTextLen (out): see GlyphHit
 290 */
 291   PRBool
 292          SmilyHit(const PRUnichar * aInString, PRInt32 aLength, PRBool col0,
 293          const char* tagTXT, const char* imageName,
 294          nsString& outputHTML, PRInt32& glyphTextLen);
 295
 296 /**
 297   Checks, if we can replace some chars at the start of line with prettier HTML
 298   code.<p>
 299   If success is reported, replace the first glyphTextLen chars with outputHTML
 300
 301   @param text (in): line of text possibly with Glyph.<p>
 302               If col0 is true,
 303                 starting with Glyph <br><!-- (br not part of text) -->
 304               else
 305                 starting one char before Glyph
 306   @param col0 (in): text starts at the beginning of the line (or paragraph)
 307   @param aOutString (out): APPENDS html for the glyph to this string
 308   @param glyphTextLen (out): Length of original text to replace
 309   @return see StructPhraseHit
 310 */
 311   PRBool GlyphHit(const PRUnichar * aInString, PRInt32 aInLength, PRBool col0,
 312        nsString& aOutString, PRInt32& glyphTextLen);
 313
 314 /**
 315   Check if a given url should be linkified.
 316   @param aURL (in): url to be checked on.
 317 */
 318   PRBool ShouldLinkify(const nsCString& aURL);
 319 };
 320
 321 // It's said, that Win32 and Mac don't like static const members
 322 const PRInt32 mozTXTToHTMLConv_lastMode = 4;
 323                                 // Needed (only) by mozTXTToHTMLConv::FindURL
 324 const PRInt32 mozTXTToHTMLConv_numberOfModes = 4;  // dito; unknown not counted
 325
 326 #endif