void
mozTXTToHTMLConv::CalculateURLBoundaries(const PRUnichar * aInString, PRInt32 aInStringLength,
const PRUint32 pos, const PRUint32 whathasbeendone,
const modetype check, const PRUint32 start, const PRUint32 end,
nsString& txtURL, nsString& desc,
PRInt32& replaceBefore, PRInt32& replaceAfter)
{
PRUint32 descstart = start;
switch(check)
{
case RFC1738:
{
descstart = start - 5;
desc.Append(&aInString[descstart], end - descstart + 2); // include "<URL:" and ">"
replaceAfter = end - pos + 1;
} break;
case RFC2396E:
{
descstart = start - 1;
desc.Append(&aInString[descstart], end - descstart + 2); // include brackets
replaceAfter = end - pos + 1;
} break;
case freetext:
case abbreviated:
{
descstart = start;
desc.Append(&aInString[descstart], end - start + 1); // don't include brackets
replaceAfter = end - pos;
} break;
default: break;
} //switch
EscapeStr(desc, false);
txtURL.Append(&aInString[start], end - start + 1);
txtURL.StripWhitespace();
// FIX ME
nsAutoString temp2;
ScanTXT(&aInString[descstart], pos - descstart, ~kURLs /*prevents loop*/ & whathasbeendone, temp2);
replaceBefore = temp2.Length();
return;
}
NS_IMETHODIMP
mozTXTToHTMLConv::ScanTXT(const PRUnichar *text, PRUint32 whattodo,
PRUnichar **_retval)
{
NS_ENSURE_ARG(text);
// FIX ME!!!
nsString outString;
PRInt32 inLength = nsCRT::strlen(text);
// by setting a large capacity up front, we save time
// when appending characters to the output string because we don't
// need to reallocate and re-copy the characters already in the out String.
NS_ASSERTION(inLength, "ScanTXT passed 0 length string");
if (inLength == 0) {
*_retval = nsCRT::strdup(text);
return NS_OK;
}
outString.SetCapacity(PRUint32(inLength * growthRate));
ScanTXT(text, inLength, whattodo, outString);
*_retval = ToNewUnicode(outString);
return *_retval ? NS_OK : NS_ERROR_OUT_OF_MEMORY;
}
void
mozTXTToHTMLConv::ScanHTML(nsString& aInString, PRUint32 whattodo, nsString &aOutString)
{
// some common variables we were recalculating
// every time inside the for loop...
PRInt32 lengthOfInString = aInString.Length();
const PRUnichar * uniBuffer = aInString.get();
#ifdef DEBUG_BenB_Perf
PRTime parsing_start = PR_IntervalNow();
#endif
// Look for simple entities not included in a tags and scan them.
/* Skip all tags ("<[...]>") and content in an a tag ("<a[...]</a>")
or in a tag ("<!--[...]-->").
Unescape the rest (text between tags) and pass it to ScanTXT. */
for (PRInt32 i = 0; i < lengthOfInString;)
{
if (aInString[i] == '<') // html tag
{
PRUint32 start = PRUint32(i);
if (nsCRT::ToLower((char)aInString[PRUint32(i) + 1]) == 'a')
// if a tag, skip until </a>
{
i = aInString.Find("</a>", true, i);
if (i == kNotFound)
i = lengthOfInString;
else
i += 4;
}
else if (aInString[PRUint32(i) + 1] == '!' && aInString[PRUint32(i) + 2] == '-' &&
aInString[PRUint32(i) + 3] == '-')
//if out-commended code, skip until -->
{
i = aInString.Find("-->", false, i);
if (i == kNotFound)
i = lengthOfInString;
else
i += 3;
}
else // just skip tag (attributes etc.)
{
i = aInString.FindChar('>', i);
if (i == kNotFound)
i = lengthOfInString;
else
i++;
}
aOutString.Append(&uniBuffer[start], PRUint32(i) - start);
}
else
{
PRUint32 start = PRUint32(i);
i = aInString.FindChar('<', i);
if (i == kNotFound)
i = lengthOfInString;
nsString tempString;
tempString.SetCapacity(PRUint32((PRUint32(i) - start) * growthRate));
UnescapeStr(uniBuffer, start, PRUint32(i) - start, tempString);
ScanTXT(tempString.get(), tempString.Length(), whattodo, aOutString);
}
}
#ifdef DEBUG_BenB_Perf
printf("ScanHTML time: %d ms\n", PR_IntervalToMilliseconds(PR_IntervalNow() - parsing_start));
#endif
}
void
mozTXTToHTMLConv::ScanHTML(nsString& aInString, uint32_t whattodo, nsString &aOutString)
{
// some common variables we were recalculating
// every time inside the for loop...
int32_t lengthOfInString = aInString.Length();
const char16_t * uniBuffer = aInString.get();
#ifdef DEBUG_BenB_Perf
PRTime parsing_start = PR_IntervalNow();
#endif
// Look for simple entities not included in a tags and scan them.
// Skip all tags ("<[...]>") and content in an a link tag ("<a [...]</a>"),
// comment tag ("<!--[...]-->"), style tag, script tag or head tag.
// Unescape the rest (text between tags) and pass it to ScanTXT.
for (int32_t i = 0; i < lengthOfInString;)
{
if (aInString[i] == '<') // html tag
{
int32_t start = i;
if (Substring(aInString, i + 1, 2).LowerCaseEqualsASCII("a "))
// if a tag, skip until </a>.
// Make sure there's a space after, not to match "abbr".
{
i = aInString.Find("</a>", true, i);
if (i == kNotFound)
i = lengthOfInString;
else
i += 4;
}
else if (Substring(aInString, i + 1, 3).LowerCaseEqualsASCII("!--"))
// if out-commended code, skip until -->
{
i = aInString.Find("-->", false, i);
if (i == kNotFound)
i = lengthOfInString;
else
i += 3;
}
else if (Substring(aInString, i + 1, 5).LowerCaseEqualsASCII("style") &&
(aInString.CharAt(i + 6) == ' ' || aInString.CharAt(i + 6) == '>'))
// if style tag, skip until </style>
{
i = aInString.Find("</style>", true, i);
if (i == kNotFound)
i = lengthOfInString;
else
i += 8;
}
else if (Substring(aInString, i + 1, 6).LowerCaseEqualsASCII("script") &&
(aInString.CharAt(i + 7) == ' ' || aInString.CharAt(i + 7) == '>'))
// if script tag, skip until </script>
{
i = aInString.Find("</script>", true, i);
if (i == kNotFound)
i = lengthOfInString;
else
i += 9;
}
else if (Substring(aInString, i + 1, 4).LowerCaseEqualsASCII("head") &&
(aInString.CharAt(i + 5) == ' ' || aInString.CharAt(i + 5) == '>'))
// if head tag, skip until </head>
// Make sure not to match <header>.
{
i = aInString.Find("</head>", true, i);
if (i == kNotFound)
i = lengthOfInString;
else
i += 7;
}
else // just skip tag (attributes etc.)
{
i = aInString.FindChar('>', i);
if (i == kNotFound)
i = lengthOfInString;
else
i++;
}
aOutString.Append(&uniBuffer[start], i - start);
}
else
{
uint32_t start = uint32_t(i);
i = aInString.FindChar('<', i);
if (i == kNotFound)
i = lengthOfInString;
nsString tempString;
tempString.SetCapacity(uint32_t((uint32_t(i) - start) * growthRate));
UnescapeStr(uniBuffer, start, uint32_t(i) - start, tempString);
ScanTXT(tempString.get(), tempString.Length(), whattodo, aOutString);
}
}
#ifdef DEBUG_BenB_Perf
printf("ScanHTML time: %d ms\n", PR_IntervalToMilliseconds(PR_IntervalNow() - parsing_start));
#endif
}
