Magic-Mirror/gecko-dev
1
0
Fork 0
mirror of https://github.com/mozilla/gecko-dev.git synced 2024-10-10 11:55:49 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

13750,13753,14075,15293,13873,12551:

Browse Source 
- Rewrite wrapping logic for plaintext output sink,
  and run all output through the wrapping/formatting Write method
  (which now has logic to determine when we should be wrapping).
- Handle blockquote type=cite mail quotes.
- Write several new regression tests for plaintext output bugs,
  and include those tests and their expected output into the
  automated output test.
r=sfraser,harishd
This commit is contained in:
akkana%netscape.com 1999-10-07 01:10:32 +00:00
parent 73d733e8c2
commit d1731dbe4e
18 changed files with 566 additions and 116 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

169
htmlparser/src/nsHTMLToTXTSinkStream.cpp
View File

@ -164,6 +164,7 @@ nsHTMLToTXTSinkStream::nsHTMLToTXTSinkStream()
NS_INIT_REFCNT();
mColPos = 0;
mIndent = 0;
mCiteQuote = PR_FALSE;
mDoOutput = PR_FALSE;
mBufferSize = 0;
mBufferLength = 0;
@ -355,6 +356,24 @@ nsHTMLToTXTSinkStream::AddComment(const nsIParserNode& aNode)
return NS_OK;
}
NS_IMETHODIMP
nsHTMLToTXTSinkStream::GetValueOfAttribute(const nsIParserNode& aNode,
char* aMatchKey,
nsString& aValueRet)
{
nsAutoString matchKey (aMatchKey);
PRInt32 count=aNode.GetAttributeCount();
for (PRInt32 i=0;i<count;i++)
{
const nsString& key = aNode.GetKeyAt(i);
if (key == matchKey)
{
aValueRet = aNode.GetValueAt(i);
return NS_OK;
}
}
return NS_ERROR_NOT_AVAILABLE;
}
/**
* This method is used to a general container.
@ -371,19 +390,13 @@ nsHTMLToTXTSinkStream::OpenContainer(const nsIParserNode& aNode)
const nsString& name = aNode.GetText();
if (name.Equals("XIF_DOC_INFO"))
{
PRInt32 count=aNode.GetAttributeCount();
for(PRInt32 i=0;i<count;i++)
nsString value;
if (NS_SUCCEEDED(GetValueOfAttribute(aNode, "charset", value)))
{
const nsString& key=aNode.GetKeyAt(i);
const nsString& value=aNode.GetValueAt(i);
if (key.Equals("charset"))
{
if (mCharsetOverride.Length() == 0)
InitEncoder(value);
else
InitEncoder(mCharsetOverride);
}
if (mCharsetOverride.Length() == 0)
InitEncoder(value);
else
InitEncoder(mCharsetOverride);
}
}
@ -427,7 +440,17 @@ nsHTMLToTXTSinkStream::OpenContainer(const nsIParserNode& aNode)
mColPos++;
}
else if (type == eHTMLTag_blockquote)
mIndent += gTabSize;
{
// Find out whether it's a type=cite, and insert "> " instead.
// Eventually we should get the value of the pref controlling citations,
// and handle AOL-style citations as well.
nsString value;
if (NS_SUCCEEDED(GetValueOfAttribute(aNode, "type", value))
&& value.StripChars("\"").Equals("cite", PR_TRUE))
mCiteQuote = PR_TRUE;
else
mIndent += gTabSize;
}
else if (type == eHTMLTag_pre)
{
nsAutoString temp(NS_LINEBREAK);
@ -489,14 +512,19 @@ nsHTMLToTXTSinkStream::CloseContainer(const nsIParserNode& aNode)
--mOLStackIndex;
else if (type == eHTMLTag_blockquote)
mIndent -= gTabSize;
{
if (mCiteQuote)
mCiteQuote = PR_FALSE;
else
mIndent -= gTabSize;
}
// End current line if we're ending a block level tag
if (IsBlockLevel(type))
{
if (mColPos != 0)
{
if (mFlags & nsIDocumentEncoder::OutputFormatted)
//if (mFlags & nsIDocumentEncoder::OutputFormatted)
{
nsAutoString temp(NS_LINEBREAK);
Write(temp);
@ -538,15 +566,7 @@ nsHTMLToTXTSinkStream::AddLeaf(const nsIParserNode& aNode)
}
#endif
if ((mFlags & nsIDocumentEncoder::OutputFormatted
|| mFlags & nsIDocumentEncoder::OutputWrap)
&& mWrapColumn > 0)
WriteWrapped(text);
else
{
Write(text);
mColPos += text.Length();
}
Write(text);
}
else if (type == eHTMLTag_entity)
{
@ -650,15 +670,16 @@ void nsHTMLToTXTSinkStream::EncodeToBuffer(const nsString& aSrc)
/**
* Write places the contents of aString into either the output stream
* WriteSimple places the contents of aString into either the output stream
* or the output string.
* When going to the stream, all data is run through the encoder
* When going to the stream, all data is run through the encoder.
* No formatting or wrapping is done here; that happens in ::Write.
*
* @updated gpk02/03/99
* @param
* @return
*/
void nsHTMLToTXTSinkStream::Write(const nsString& aString)
void nsHTMLToTXTSinkStream::WriteSimple(const nsString& aString)
{
// If a encoder is being used then convert first convert the input string
if (mUnicodeEncoder != nsnull)
@ -696,51 +717,86 @@ void nsHTMLToTXTSinkStream::Write(const nsString& aString)
//
// Write a string, wrapping appropriately to mWrapColumn.
// This routine also handles indentation and mail-quoting,
// and so should be used for formatted output even if we're not wrapping.
//
void
nsHTMLToTXTSinkStream::WriteWrapped(const nsString& aString)
nsHTMLToTXTSinkStream::Write(const nsString& aString)
{
#ifdef DEBUG_wrapping
char* foo = aString.ToNewCString();
printf("WriteWrapped(%s): wrap col = %d\n", foo, mWrapColumn);
printf("Write(%s): wrap col = %d, mColPos = %d\n", foo, mWrapColumn, mColPos);
nsAllocator::Free(foo);
#endif
PRInt32 bol = 0;
int totLen = aString.Length();
while (bol < totLen) // Loop over lines
{
#ifdef DEBUG_wrapping
nsString remaining;
aString.Right(remaining, totLen - bol);
foo = remaining.ToNewCString();
printf("Next line: bol = %d, totLen = %d, string = '%s'\n",
bol, totLen, foo);
nsAllocator::Free(foo);
#endif
// Indent at the beginning of the line, if necessary
if (mColPos == 0 && mIndent > 0)
// Put the mail quote "> " chars in, if appropriate:
if (mColPos == 0)
{
if (mCiteQuote)
{
nsAutoString temp("> ");
WriteSimple(temp);
mColPos += 2;
}
// Indent if necessary
if (mIndent > 0)
{
char* spaces = NS_STATIC_CAST(char*, nsAllocator::Alloc(mIndent+1));
for (int i=0; i<mIndent; ++i)
spaces[i] = ' ';
spaces[mIndent] = '\0';
nsAutoString temp(spaces);
Write (temp);
WriteSimple(temp);
mColPos += mIndent;
nsAllocator::Free(spaces);
}
}
// See if there's a newline in the string:
PRInt32 newline = aString.FindCharInSet("\n\r", bol);
// Don't wrap mail-quoted text
PRUint32 wrapcol = (mCiteQuote ? 0 : mWrapColumn);
// See if there's a newline in the string:
PRInt32 newline = aString.FindCharInSet("\n\r", bol);
if ((!(mFlags & nsIDocumentEncoder::OutputFormatted)
&& !(mFlags & nsIDocumentEncoder::OutputWrap))
|| wrapcol == 0)
{
WriteSimple(aString);
// Simple attempt to be smart about col pos:
if (newline >= 0)
mColPos = totLen - newline - 1;
else
mColPos += totLen;
#ifdef DEBUG_wrapping
printf("No wrapping: newline is %d, totLen is %d; leaving mColPos = %d\n",
newline, totLen, mColPos);
#endif
return;
}
while (bol < totLen) // Loop over lines
{
#ifdef DEBUG_wrapping
nsString remaining;
aString.Right(remaining, totLen - bol);
foo = remaining.ToNewCString();
printf("Next line: bol = %d, newline = %d, totLen = %d, string = '%s'\n",
bol, newline, totLen, foo);
nsAllocator::Free(foo);
#endif
// Set eol to the end of the string or the first newline,
// whichever comes first:
int eol = bol + mWrapColumn - mColPos;
int eol = bol + wrapcol - mColPos;
if (eol > totLen || wrapcol == 0)
eol = bol + totLen;
if (eol > totLen)
eol = totLen;
else if (newline > 0 && eol > newline)
eol = newline;
// else we have to wrap
@ -773,11 +829,11 @@ nsHTMLToTXTSinkStream::WriteWrapped(const nsString& aString)
if (mColPos > mIndent)
{
nsAutoString linebreak(NS_LINEBREAK);
Write(linebreak);
WriteSimple(linebreak);
mColPos = 0;
continue;
}
#endif /* CONFUSED */
#endif /* NOTSURE */
// Else apparently we really can't break this line at whitespace --
// so scan forward to the next space or newline, and dump a long line.
@ -786,9 +842,8 @@ nsHTMLToTXTSinkStream::WriteWrapped(const nsString& aString)
&& (newline < 0 || eol < newline))
{
#ifdef DEBUG_wrapping
nsString linestr;
aString.Mid(linestr, bol, lastSpace - bol);
foo = linestr.ToNewCString();
aString.Mid(remaining, bol, lastSpace - bol);
foo = remaining.ToNewCString();
printf("Searching foreward: '%c' is not a space\n line = '%s'\n",
(char)aString[lastSpace], foo);
nsAllocator::Free(foo);
@ -817,8 +872,16 @@ nsHTMLToTXTSinkStream::WriteWrapped(const nsString& aString)
}
else // Not wrapping and not writing a newline
mColPos += lineStr.Length();
Write(lineStr);
WriteSimple(lineStr);
#ifdef DEBUG_wrapping
foo = lineStr.ToNewCString();
printf("Calling WriteSimple(%s), leaving mColPos = %d\n", foo, mColPos);
nsAllocator::Free(foo);
#endif
// Reset bol and newline:
bol = eol+1;
newline = aString.FindCharInSet("\n\r", bol);
} // Continue looping over the string
}

6
htmlparser/src/nsHTMLToTXTSinkStream.h
View File

@ -137,15 +137,19 @@ protected:
nsresult InitEncoder(const nsString& aCharset);
void WriteSimple(const nsString& aString);
void Write(const nsString& aString);
void WriteWrapped(const nsString& aString);
void EncodeToBuffer(const nsString& aString);
NS_IMETHOD GetValueOfAttribute(const nsIParserNode& aNode,
char* aMatchKey,
nsString& aValueRet);
protected:
nsIOutputStream* mStream;
nsString* mString;
PRInt32 mIndent;
PRBool mCiteQuote;
PRInt32 mColPos;
PRBool mDoOutput;
PRInt32 mFlags;

2
htmlparser/tests/outsinks/Makefile.in
View File

@ -44,6 +44,8 @@ TEST_FILES = \
entityxif.out \
mailquote.html \
mailquote.out \
xifstuff.xif \
xifstuff.out \
$(NULL)
include $(topsrcdir)/config/rules.mk

14
htmlparser/tests/outsinks/TestOutSinks
View File

@ -27,6 +27,13 @@
set errmsg = ""
echo "Testing simple html to html ..."
TestOutput -i text/html -o text/html -c OutTestData/simple.html OutTestData/simple.html
if ($status != 0) then
echo "Simple html to html failed.\n"
set errmsg = ($errmsg "simple.html")
endif
echo "Testing simple copy cases ..."
TestOutput -i text/html -o text/plain -f 0 -w 0 -c OutTestData/simplecopy.out OutTestData/simple.html
if ($status != 0) then
@ -62,6 +69,13 @@ if ($status != 0) then
set errmsg = ($errmsg "entityxif.out")
endif
echo "Testing XIF to HTML ..."
TestOutput -i text/xif -o text/html -c OutTestData/xifstuff.out OutTestData/xifstuff.xif
if ($status != 0) then
echo "XIF entity convertsion test failed."
set errmsg = ($errmsg "entityxif.out")
endif
if (errmsg != "") then
echo " "
echo TESTS FAILED: $errmsg

16
htmlparser/tests/outsinks/makefile.win
View File

@ -26,13 +26,26 @@ OBJS = \
.\$(OBJDIR)\nsSetupRegistry.obj \
$(NULL)
TEST_FILES = \
plain.html \
plainwrap.out \
plainnowrap.out \
simple.html \
simplecopy.out \
entityxif.xif \
entityxif.out \
mailquote.html \
mailquote.out \
xifstuff.xif \
xifstuff.out \
$(NULL)
LINCS= \
-I$(PUBLIC)\raptor \
-I$(PUBLIC)\xpcom \
-I$(PUBLIC)\netlib
LLIBS= \
$(DIST)\lib\raptorhtmlpars.lib \
$(DIST)\lib\xpcom.lib \
$(LIBNSPR) \
$(NULL)
@ -47,6 +60,7 @@ include <$(DEPTH)\config\rules.mak>
install:: $(PROGRAM)
$(MAKE_INSTALL) $(PROGRAM) $(DIST)\bin
$(MAKE_INSTALL) $(TEST_FILES) $(DIST)/bin/OutTestData
clobber::
rm -f $(OBJS) $(DIST)\bin\Convert.exe

6
htmlparser/tests/outsinks/simple.html
View File

@ -1,5 +1,6 @@
<html>
<head><!--
<head>
<!--
-- The contents of this file are subject to the Netscape Public
-- License Version 1.1 (the "License"); you may not use this file
-- except in compliance with the License. You may obtain a copy of
@ -32,7 +33,8 @@ Here is some <u>underlined and <b>bold</b>ened</u>ified text.
<p>
Here is a line ending with a space
followed by a line break.
The output should contain only one space between "space" and "followed".
The output should contain only one space (and no line breaks) between "space" and "followed".
</p>
</body>
</html>

2
htmlparser/tests/outsinks/simplecopy.out
View File

@ -1,3 +1,3 @@
Simple html page Here is a link to mozilla.org. Here is some underlined and boldenedified text.
Here is a line ending with a space followed by a line break. The output should contain only one space between "space" and "followed".
Here is a line ending with a space followed by a line break. The output should contain only one space (and no line breaks) between "space" and "followed".

42
htmlparser/tests/outsinks/xifstuff.out Normal file
View File

@ -0,0 +1,42 @@
<html>
<head>
<!--
-- The contents of this file are subject to the Netscape Public
-- License Version 1.1 (the "License"); you may not use this file
-- except in compliance with the License. You may obtain a copy of
-- the License at http://www.mozilla.org/NPL/
--
-- Software distributed under the License is distributed on an "AS
-- IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
-- implied. See the License for the specific language governing
-- rights and limitations under the License.
--
-- The Original Code is Mozilla Communicator client code, released
-- March 31, 1998.
--
-- The Initial Developer of the Original Code is Netscape
-- Communications Corporation. Portions created by Netscape are
-- Copyright (C) 1998-1999 Netscape Communications Corporation. All
-- Rights Reserved.
--
-- Contributor(s):
-->
<title>XIF Test Page</title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<h2>Here's the deal...</h2>
<p>This is a good place to add in <b>html</b> to aid in testing features
under development. It's also a great place to not use latin.
<!-- This is a comment;
Here is more of the comment.
-->
</p></body>

84
htmlparser/tests/outsinks/xifstuff.xif Normal file
View File

@ -0,0 +1,84 @@
<?xml version="1.0"?>
<!DOCTYPE xif>
<encode selection="0"/>
<section>
<section_head>
<document_info charset="UTF-8"/>
</section_head>
<section_body>
<container isa="html">
<container isa="head">
<content>
</content>
<comment><content>
-- The contents of this file are subject to the Netscape Public
-- License Version 1.1 (the "License"); you may not use this file
-- except in compliance with the License. You may obtain a copy of
-- the License at http://www.mozilla.org/NPL/
--
-- Software distributed under the License is distributed on an "AS
-- IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
-- implied. See the License for the specific language governing
-- rights and limitations under the License.
--
-- The Original Code is Mozilla Communicator client code, released
-- March 31, 1998.
--
-- The Initial Developer of the Original Code is Netscape
-- Communications Corporation. Portions created by Netscape are
-- Copyright (C) 1998-1999 Netscape Communications Corporation. All
-- Rights Reserved.
--
-- Contributor(s):
</content>
</comment>
<content>
</content>
<container isa="title">
<content>XIF Test Page</content>
</container><!--title-->
<content>
</content>
<leaf isa="meta">
<attr name="http-equiv" value="Content-Type"/>
<attr name="content" value="text/html; charset=utf-8"/>
</leaf><!--meta-->
</container><!--head-->
<content>
</content>
<container isa="body">
<container isa="h2">
<content>Here's the deal...</content>
</container><!--h2-->
<content>
</content>
<container isa="p">
<content>This is a good place to add in </content>
<container isa="b">
<content>html</content>
</container><!--b-->
<content> to aid in testing features
under development. It's also a great place to not use latin.
</content>
<comment><content> This is a comment;
Here is more of the comment.
</content>
</comment>
<content>
</content>
</container><!--body-->
</container><!--html-->
</section_body>
</section>

169
parser/htmlparser/src/nsHTMLToTXTSinkStream.cpp
View File

@ -164,6 +164,7 @@ nsHTMLToTXTSinkStream::nsHTMLToTXTSinkStream()
NS_INIT_REFCNT();
mColPos = 0;
mIndent = 0;
mCiteQuote = PR_FALSE;
mDoOutput = PR_FALSE;
mBufferSize = 0;
mBufferLength = 0;
@ -355,6 +356,24 @@ nsHTMLToTXTSinkStream::AddComment(const nsIParserNode& aNode)
return NS_OK;
}
NS_IMETHODIMP
nsHTMLToTXTSinkStream::GetValueOfAttribute(const nsIParserNode& aNode,
char* aMatchKey,
nsString& aValueRet)
{
nsAutoString matchKey (aMatchKey);
PRInt32 count=aNode.GetAttributeCount();
for (PRInt32 i=0;i<count;i++)
{
const nsString& key = aNode.GetKeyAt(i);
if (key == matchKey)
{
aValueRet = aNode.GetValueAt(i);
return NS_OK;
}
}
return NS_ERROR_NOT_AVAILABLE;
}
/**
* This method is used to a general container.
@ -371,19 +390,13 @@ nsHTMLToTXTSinkStream::OpenContainer(const nsIParserNode& aNode)
const nsString& name = aNode.GetText();
if (name.Equals("XIF_DOC_INFO"))
{
PRInt32 count=aNode.GetAttributeCount();
for(PRInt32 i=0;i<count;i++)
nsString value;
if (NS_SUCCEEDED(GetValueOfAttribute(aNode, "charset", value)))
{
const nsString& key=aNode.GetKeyAt(i);
const nsString& value=aNode.GetValueAt(i);
if (key.Equals("charset"))
{
if (mCharsetOverride.Length() == 0)
InitEncoder(value);
else
InitEncoder(mCharsetOverride);
}
if (mCharsetOverride.Length() == 0)
InitEncoder(value);
else
InitEncoder(mCharsetOverride);
}
}
@ -427,7 +440,17 @@ nsHTMLToTXTSinkStream::OpenContainer(const nsIParserNode& aNode)
mColPos++;
}
else if (type == eHTMLTag_blockquote)
mIndent += gTabSize;
{
// Find out whether it's a type=cite, and insert "> " instead.
// Eventually we should get the value of the pref controlling citations,
// and handle AOL-style citations as well.
nsString value;
if (NS_SUCCEEDED(GetValueOfAttribute(aNode, "type", value))
&& value.StripChars("\"").Equals("cite", PR_TRUE))
mCiteQuote = PR_TRUE;
else
mIndent += gTabSize;
}
else if (type == eHTMLTag_pre)
{
nsAutoString temp(NS_LINEBREAK);
@ -489,14 +512,19 @@ nsHTMLToTXTSinkStream::CloseContainer(const nsIParserNode& aNode)
--mOLStackIndex;
else if (type == eHTMLTag_blockquote)
mIndent -= gTabSize;
{
if (mCiteQuote)
mCiteQuote = PR_FALSE;
else
mIndent -= gTabSize;
}
// End current line if we're ending a block level tag
if (IsBlockLevel(type))
{
if (mColPos != 0)
{
if (mFlags & nsIDocumentEncoder::OutputFormatted)
//if (mFlags & nsIDocumentEncoder::OutputFormatted)
{
nsAutoString temp(NS_LINEBREAK);
Write(temp);
@ -538,15 +566,7 @@ nsHTMLToTXTSinkStream::AddLeaf(const nsIParserNode& aNode)
}
#endif
if ((mFlags & nsIDocumentEncoder::OutputFormatted
|| mFlags & nsIDocumentEncoder::OutputWrap)
&& mWrapColumn > 0)
WriteWrapped(text);
else
{
Write(text);
mColPos += text.Length();
}
Write(text);
}
else if (type == eHTMLTag_entity)
{
@ -650,15 +670,16 @@ void nsHTMLToTXTSinkStream::EncodeToBuffer(const nsString& aSrc)
/**
* Write places the contents of aString into either the output stream
* WriteSimple places the contents of aString into either the output stream
* or the output string.
* When going to the stream, all data is run through the encoder
* When going to the stream, all data is run through the encoder.
* No formatting or wrapping is done here; that happens in ::Write.
*
* @updated gpk02/03/99
* @param
* @return
*/
void nsHTMLToTXTSinkStream::Write(const nsString& aString)
void nsHTMLToTXTSinkStream::WriteSimple(const nsString& aString)
{
// If a encoder is being used then convert first convert the input string
if (mUnicodeEncoder != nsnull)
@ -696,51 +717,86 @@ void nsHTMLToTXTSinkStream::Write(const nsString& aString)
//
// Write a string, wrapping appropriately to mWrapColumn.
// This routine also handles indentation and mail-quoting,
// and so should be used for formatted output even if we're not wrapping.
//
void
nsHTMLToTXTSinkStream::WriteWrapped(const nsString& aString)
nsHTMLToTXTSinkStream::Write(const nsString& aString)
{
#ifdef DEBUG_wrapping
char* foo = aString.ToNewCString();
printf("WriteWrapped(%s): wrap col = %d\n", foo, mWrapColumn);
printf("Write(%s): wrap col = %d, mColPos = %d\n", foo, mWrapColumn, mColPos);
nsAllocator::Free(foo);
#endif
PRInt32 bol = 0;
int totLen = aString.Length();
while (bol < totLen) // Loop over lines
{
#ifdef DEBUG_wrapping
nsString remaining;
aString.Right(remaining, totLen - bol);
foo = remaining.ToNewCString();
printf("Next line: bol = %d, totLen = %d, string = '%s'\n",
bol, totLen, foo);
nsAllocator::Free(foo);
#endif
// Indent at the beginning of the line, if necessary
if (mColPos == 0 && mIndent > 0)
// Put the mail quote "> " chars in, if appropriate:
if (mColPos == 0)
{
if (mCiteQuote)
{
nsAutoString temp("> ");
WriteSimple(temp);
mColPos += 2;
}
// Indent if necessary
if (mIndent > 0)
{
char* spaces = NS_STATIC_CAST(char*, nsAllocator::Alloc(mIndent+1));
for (int i=0; i<mIndent; ++i)
spaces[i] = ' ';
spaces[mIndent] = '\0';
nsAutoString temp(spaces);
Write (temp);
WriteSimple(temp);
mColPos += mIndent;
nsAllocator::Free(spaces);
}
}
// See if there's a newline in the string:
PRInt32 newline = aString.FindCharInSet("\n\r", bol);
// Don't wrap mail-quoted text
PRUint32 wrapcol = (mCiteQuote ? 0 : mWrapColumn);
// See if there's a newline in the string:
PRInt32 newline = aString.FindCharInSet("\n\r", bol);
if ((!(mFlags & nsIDocumentEncoder::OutputFormatted)
&& !(mFlags & nsIDocumentEncoder::OutputWrap))
|| wrapcol == 0)
{
WriteSimple(aString);
// Simple attempt to be smart about col pos:
if (newline >= 0)
mColPos = totLen - newline - 1;
else
mColPos += totLen;
#ifdef DEBUG_wrapping
printf("No wrapping: newline is %d, totLen is %d; leaving mColPos = %d\n",
newline, totLen, mColPos);
#endif
return;
}
while (bol < totLen) // Loop over lines
{
#ifdef DEBUG_wrapping
nsString remaining;
aString.Right(remaining, totLen - bol);
foo = remaining.ToNewCString();
printf("Next line: bol = %d, newline = %d, totLen = %d, string = '%s'\n",
bol, newline, totLen, foo);
nsAllocator::Free(foo);
#endif
// Set eol to the end of the string or the first newline,
// whichever comes first:
int eol = bol + mWrapColumn - mColPos;
int eol = bol + wrapcol - mColPos;
if (eol > totLen || wrapcol == 0)
eol = bol + totLen;
if (eol > totLen)
eol = totLen;
else if (newline > 0 && eol > newline)
eol = newline;
// else we have to wrap
@ -773,11 +829,11 @@ nsHTMLToTXTSinkStream::WriteWrapped(const nsString& aString)
if (mColPos > mIndent)
{
nsAutoString linebreak(NS_LINEBREAK);
Write(linebreak);
WriteSimple(linebreak);
mColPos = 0;
continue;
}
#endif /* CONFUSED */
#endif /* NOTSURE */
// Else apparently we really can't break this line at whitespace --
// so scan forward to the next space or newline, and dump a long line.
@ -786,9 +842,8 @@ nsHTMLToTXTSinkStream::WriteWrapped(const nsString& aString)
&& (newline < 0 || eol < newline))
{
#ifdef DEBUG_wrapping
nsString linestr;
aString.Mid(linestr, bol, lastSpace - bol);
foo = linestr.ToNewCString();
aString.Mid(remaining, bol, lastSpace - bol);
foo = remaining.ToNewCString();
printf("Searching foreward: '%c' is not a space\n line = '%s'\n",
(char)aString[lastSpace], foo);
nsAllocator::Free(foo);
@ -817,8 +872,16 @@ nsHTMLToTXTSinkStream::WriteWrapped(const nsString& aString)
}
else // Not wrapping and not writing a newline
mColPos += lineStr.Length();
Write(lineStr);
WriteSimple(lineStr);
#ifdef DEBUG_wrapping
foo = lineStr.ToNewCString();
printf("Calling WriteSimple(%s), leaving mColPos = %d\n", foo, mColPos);
nsAllocator::Free(foo);
#endif
// Reset bol and newline:
bol = eol+1;
newline = aString.FindCharInSet("\n\r", bol);
} // Continue looping over the string
}

6
parser/htmlparser/src/nsHTMLToTXTSinkStream.h
View File

@ -137,15 +137,19 @@ protected:
nsresult InitEncoder(const nsString& aCharset);
void WriteSimple(const nsString& aString);
void Write(const nsString& aString);
void WriteWrapped(const nsString& aString);
void EncodeToBuffer(const nsString& aString);
NS_IMETHOD GetValueOfAttribute(const nsIParserNode& aNode,
char* aMatchKey,
nsString& aValueRet);
protected:
nsIOutputStream* mStream;
nsString* mString;
PRInt32 mIndent;
PRBool mCiteQuote;
PRInt32 mColPos;
PRBool mDoOutput;
PRInt32 mFlags;

2
parser/htmlparser/tests/outsinks/Makefile.in
View File

@ -44,6 +44,8 @@ TEST_FILES = \
entityxif.out \
mailquote.html \
mailquote.out \
xifstuff.xif \
xifstuff.out \
$(NULL)
include $(topsrcdir)/config/rules.mk

14
parser/htmlparser/tests/outsinks/TestOutSinks
View File

@ -27,6 +27,13 @@
set errmsg = ""
echo "Testing simple html to html ..."
TestOutput -i text/html -o text/html -c OutTestData/simple.html OutTestData/simple.html
if ($status != 0) then
echo "Simple html to html failed.\n"
set errmsg = ($errmsg "simple.html")
endif
echo "Testing simple copy cases ..."
TestOutput -i text/html -o text/plain -f 0 -w 0 -c OutTestData/simplecopy.out OutTestData/simple.html
if ($status != 0) then
@ -62,6 +69,13 @@ if ($status != 0) then
set errmsg = ($errmsg "entityxif.out")
endif
echo "Testing XIF to HTML ..."
TestOutput -i text/xif -o text/html -c OutTestData/xifstuff.out OutTestData/xifstuff.xif
if ($status != 0) then
echo "XIF entity convertsion test failed."
set errmsg = ($errmsg "entityxif.out")
endif
if (errmsg != "") then
echo " "
echo TESTS FAILED: $errmsg

16
parser/htmlparser/tests/outsinks/makefile.win
View File

@ -26,13 +26,26 @@ OBJS = \
.\$(OBJDIR)\nsSetupRegistry.obj \
$(NULL)
TEST_FILES = \
plain.html \
plainwrap.out \
plainnowrap.out \
simple.html \
simplecopy.out \
entityxif.xif \
entityxif.out \
mailquote.html \
mailquote.out \
xifstuff.xif \
xifstuff.out \
$(NULL)
LINCS= \
-I$(PUBLIC)\raptor \
-I$(PUBLIC)\xpcom \
-I$(PUBLIC)\netlib
LLIBS= \
$(DIST)\lib\raptorhtmlpars.lib \
$(DIST)\lib\xpcom.lib \
$(LIBNSPR) \
$(NULL)
@ -47,6 +60,7 @@ include <$(DEPTH)\config\rules.mak>
install:: $(PROGRAM)
$(MAKE_INSTALL) $(PROGRAM) $(DIST)\bin
$(MAKE_INSTALL) $(TEST_FILES) $(DIST)/bin/OutTestData
clobber::
rm -f $(OBJS) $(DIST)\bin\Convert.exe

6
parser/htmlparser/tests/outsinks/simple.html
View File

@ -1,5 +1,6 @@
<html>
<head><!--
<head>
<!--
-- The contents of this file are subject to the Netscape Public
-- License Version 1.1 (the "License"); you may not use this file
-- except in compliance with the License. You may obtain a copy of
@ -32,7 +33,8 @@ Here is some <u>underlined and <b>bold</b>ened</u>ified text.
<p>
Here is a line ending with a space
followed by a line break.
The output should contain only one space between "space" and "followed".
The output should contain only one space (and no line breaks) between "space" and "followed".
</p>
</body>
</html>

2
parser/htmlparser/tests/outsinks/simplecopy.out
View File

@ -1,3 +1,3 @@
Simple html page Here is a link to mozilla.org. Here is some underlined and boldenedified text.
Here is a line ending with a space followed by a line break. The output should contain only one space between "space" and "followed".
Here is a line ending with a space followed by a line break. The output should contain only one space (and no line breaks) between "space" and "followed".

42
parser/htmlparser/tests/outsinks/xifstuff.out Normal file
View File

@ -0,0 +1,42 @@
<html>
<head>
<!--
-- The contents of this file are subject to the Netscape Public
-- License Version 1.1 (the "License"); you may not use this file
-- except in compliance with the License. You may obtain a copy of
-- the License at http://www.mozilla.org/NPL/
--
-- Software distributed under the License is distributed on an "AS
-- IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
-- implied. See the License for the specific language governing
-- rights and limitations under the License.
--
-- The Original Code is Mozilla Communicator client code, released
-- March 31, 1998.
--
-- The Initial Developer of the Original Code is Netscape
-- Communications Corporation. Portions created by Netscape are
-- Copyright (C) 1998-1999 Netscape Communications Corporation. All
-- Rights Reserved.
--
-- Contributor(s):
-->
<title>XIF Test Page</title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<h2>Here's the deal...</h2>
<p>This is a good place to add in <b>html</b> to aid in testing features
under development. It's also a great place to not use latin.
<!-- This is a comment;
Here is more of the comment.
-->
</p></body>

84
parser/htmlparser/tests/outsinks/xifstuff.xif Normal file
View File

@ -0,0 +1,84 @@
<?xml version="1.0"?>
<!DOCTYPE xif>
<encode selection="0"/>
<section>
<section_head>
<document_info charset="UTF-8"/>
</section_head>
<section_body>
<container isa="html">
<container isa="head">
<content>
</content>
<comment><content>
-- The contents of this file are subject to the Netscape Public
-- License Version 1.1 (the "License"); you may not use this file
-- except in compliance with the License. You may obtain a copy of
-- the License at http://www.mozilla.org/NPL/
--
-- Software distributed under the License is distributed on an "AS
-- IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
-- implied. See the License for the specific language governing
-- rights and limitations under the License.
--
-- The Original Code is Mozilla Communicator client code, released
-- March 31, 1998.
--
-- The Initial Developer of the Original Code is Netscape
-- Communications Corporation. Portions created by Netscape are
-- Copyright (C) 1998-1999 Netscape Communications Corporation. All
-- Rights Reserved.
--
-- Contributor(s):
</content>
</comment>
<content>
</content>
<container isa="title">
<content>XIF Test Page</content>
</container><!--title-->
<content>
</content>
<leaf isa="meta">
<attr name="http-equiv" value="Content-Type"/>
<attr name="content" value="text/html; charset=utf-8"/>
</leaf><!--meta-->
</container><!--head-->
<content>
</content>
<container isa="body">
<container isa="h2">
<content>Here's the deal...</content>
</container><!--h2-->
<content>
</content>
<container isa="p">
<content>This is a good place to add in </content>
<container isa="b">
<content>html</content>
</container><!--b-->
<content> to aid in testing features
under development. It's also a great place to not use latin.
</content>
<comment><content> This is a comment;
Here is more of the comment.
</content>
</comment>
<content>
</content>
</container><!--body-->
</container><!--html-->
</section_body>
</section>