Add vestigal support for Gutenberg Word Processor formatting

app/Main.cpp

@@ -2644,6 +2644,8 @@ MainWindow::ConfigureReformatFromPreferences(ReformatHolder* pReformat)
 		pPreferences->GetPrefBool(kPrConvGWP));
 	pReformat->SetReformatAllowed(ReformatHolder::kReformatMagicWindow,
 		pPreferences->GetPrefBool(kPrConvText8));
+	pReformat->SetReformatAllowed(ReformatHolder::kReformatGutenberg,
+		pPreferences->GetPrefBool(kPrConvGutenberg));
 	pReformat->SetReformatAllowed(ReformatHolder::kReformatAWP,
 		pPreferences->GetPrefBool(kPrConvAWP));
 	pReformat->SetReformatAllowed(ReformatHolder::kReformatAWP,
@@ -2707,7 +2709,13 @@ MainWindow::ConfigureReformatFromPreferences(ReformatHolder* pReformat)
 /*static*/ ReformatHolder::SourceFormat
 MainWindow::ReformatterSourceFormat(DiskImg::FSFormat format)
 {
-	if (DiskImg::UsesDOSFileStructure(format))
+	/*
+	 * Gutenberg both UsesDOSFileStructure and is formatted with 
+	 * kFormatGutenberg, so check for the latter first.
+	 */
+	if (format == DiskImg::kFormatGutenberg)
+		return ReformatHolder::kSourceFormatGutenberg;
+	else if (DiskImg::UsesDOSFileStructure(format))
 		return ReformatHolder::kSourceFormatDOS;
 	else if (format == DiskImg::kFormatCPM)
 		return ReformatHolder::kSourceFormatCPM;

app/Preferences.cpp

@@ -118,6 +118,7 @@ const Preferences::PrefMap Preferences::fPrefMaps[kPrefNumLastEntry] = {
 	{ kPrConvBusiness,					kBool,	kPrefsSect,		_T("conv-business") },
 	{ kPrConvGWP,						kBool,	kPrefsSect,		_T("conv-gwp") },
 	{ kPrConvText8,						kBool,	kPrefsSect,		_T("conv-text8") },
+	{ kPrConvGutenberg,					kBool,	kPrefsSect,		_T("conv-gutenberg") },
 	{ kPrConvAWP,						kBool,	kPrefsSect,		_T("conv-awp") },
 	{ kPrConvADB,						kBool,	kPrefsSect,		_T("conv-adb") },
 	{ kPrConvASP,						kBool,	kPrefsSect,		_T("conv-asp") },
@@ -227,6 +228,7 @@ Preferences::Preferences(void)
 	SetPrefBool(kPrConvBusiness, true);
 	SetPrefBool(kPrConvGWP, true);
 	SetPrefBool(kPrConvText8, true);
+	SetPrefBool(kPrConvGutenberg, true);
 	SetPrefBool(kPrConvAWP, true);
 	SetPrefBool(kPrConvADB, true);
 	SetPrefBool(kPrConvASP, true);

app/Preferences.h

@@ -171,6 +171,7 @@ typedef enum {
 	kPrConvBusiness,				// bool
 	kPrConvGWP,						// bool
 	kPrConvText8,					// bool
+	kPrConvGutenberg,				// bool
 	kPrConvAWP,						// bool
 	kPrConvADB,						// bool
 	kPrConvASP,						// bool

reformat/Reformat.cpp

@@ -86,6 +86,7 @@ ReformatHolder::GetReformatInstance(ReformatID id)
 	case kReformatSHR_DG3200:		pReformat = new ReformatDG3200SHR;			break;
 	case kReformatPrintShop:		pReformat = new ReformatPrintShop;			break;
 	case kReformatMacPaint:			pReformat = new ReformatMacPaint;			break;
+	case kReformatGutenberg:		pReformat = new ReformatGutenberg;			break;
 	case kReformatUnknown:
 	case kReformatMAX:
 	default:						assert(false);								break;
@@ -191,6 +192,9 @@ ReformatHolder::GetReformatName(ReformatID id)
 	case kReformatMagicWindow:
 		descr = "Magic Window";
 		break;
+	case kReformatGutenberg:
+		descr = "Gutenberg Word Processor";
+		break;
 	case kReformatAWP:
 		descr = "AppleWorks Word Processor";
 		break;

reformat/Reformat.h

@@ -1,5 +1,6 @@
 /*
  * CiderPress
+ * Copyright (C) 2009 by CiderPress authors.  All Rights Reserved.
  * Copyright (C) 2007, 2008 by faddenSoft, LLC.  All Rights Reserved.
  * See the file LICENSE for distribution terms.
  */
@@ -96,6 +97,7 @@ public:
 		kReformatGWP,
 
 		kReformatMagicWindow,
+		kReformatGutenberg,
 
 		kReformatAWP,
 		kReformatADB,
@@ -182,12 +184,14 @@ public:
 	 *
 	 * We want to know if it's DOS so we can relax some file-type checking,
 	 * and we want to know if it's CP/M so we can adjust the way we think
-	 * about text files.
+	 * about text files.  We want to know if it's Gutenberg because they only
+	 * have one type of file, and it's indistingusihable from any other text file!
 	 */
 	typedef enum SourceFormat {
 		kSourceFormatGeneric = 0,
 		kSourceFormatDOS,
 		kSourceFormatCPM,
+		kSourceFormatGutenberg,
 	} SourceFormat;
 
 
@@ -268,6 +272,7 @@ public:
 	friend class ReformatTeach;
 	friend class ReformatGWP;
 	friend class ReformatMagicWindow;
+	friend class ReformatGutenberg;
 	friend class ReformatAWP;
 	friend class ReformatADB;
 	friend class ReformatASP;

reformat/ReformatBase.h

@@ -314,6 +314,8 @@ protected:
 
 	void ConvertEOL(const unsigned char* srcBuf, long srcLen,
 		bool stripHiBits);
+	void ConvertEOL(const unsigned char* srcBuf, long srcLen,
+		bool stripHiBits, bool stripNulls);
 	void BufHexDump(const unsigned char* srcBuf, long srcLen);
 	void SetResultBuffer(ReformatOutput* pOutput, bool multiFont = false);
 

reformat/Text8.cpp

@@ -1,174 +1,225 @@
-/*
+/*
- * CiderPress
+ * CiderPress
- * Copyright (C) 2007 by faddenSoft, LLC.  All Rights Reserved.
+ * Copyright (C) 2009 by CiderPress authors.  All Rights Reserved.
- * See the file LICENSE for distribution terms.
+ * Copyright (C) 2007 by faddenSoft, LLC.  All Rights Reserved.
- */
+ * See the file LICENSE for distribution terms.
-/*
+ */
- * Convert 8-bit word processor files.
+/*
- *
+ * Convert 8-bit word processor files.
- * Most formats convert reasonably well with "Converted Text", but this
+ *
- * allows the files to be handled more transparently (e.g. Magic Window
+ * Most formats convert reasonably well with "Converted Text", but this
- * "formatted files", which can be mistaken for code.
+ * allows the files to be handled more transparently (e.g. Magic Window
- */
+ * "formatted files", which can be mistaken for code.
-#include "StdAfx.h"
+ */
-#include "Text8.h"
+#include "StdAfx.h"
-
+#include "Text8.h"
-
+
-/*
+
- * ===========================================================================
+/*
- *		Magic Window / Magic Window II
+ * ===========================================================================
- * ===========================================================================
+ *		Magic Window / Magic Window II
- */
+ * ===========================================================================
-
+ */
-/*
+
- * Magic Window and Magic Window II appear to use the same format for their
+/*
- * "formatted files".  The files are of type 'B', with a valid address field,
+ * Magic Window and Magic Window II appear to use the same format for their
- * and what looks like junk in the length field.  The files have a 256-byte
+ * "formatted files".  The files are of type 'B', with a valid address field,
- * header that seems to hold some sort of title string as well as some
+ * and what looks like junk in the length field.  The files have a 256-byte
- * binary goodies that I'm not sure what they are.
+ * header that seems to hold some sort of title string as well as some
- *
+ * binary goodies that I'm not sure what they are.
- * The data from offset 256 on is entirely mixed-case high-ASCII text.  It
+ *
- * may contain printer-specific escape codes for bold, italic, etc.
+ * The data from offset 256 on is entirely mixed-case high-ASCII text.  It
- *
+ * may contain printer-specific escape codes for bold, italic, etc.
- * A ".MW" filename suffix is enforced by the program.
+ *
- */
+ * A ".MW" filename suffix is enforced by the program.
-
+ */
-/*
+
- * Decide whether or not we want to handle this file.
+/*
- */
+ * Decide whether or not we want to handle this file.
-void
+ */
-ReformatMagicWindow::Examine(ReformatHolder* pHolder)
+void
-{
+ReformatMagicWindow::Examine(ReformatHolder* pHolder)
-	if (pHolder->GetFileType() == kTypeBIN) {
+{
-		bool isMW = ReformatMagicWindow::IsFormatted(pHolder);
+	if (pHolder->GetFileType() == kTypeBIN) {
-		bool isDotMW = strcasecmp(pHolder->GetNameExt(), ".MW") == 0;
+		bool isMW = ReformatMagicWindow::IsFormatted(pHolder);
-
+		bool isDotMW = strcasecmp(pHolder->GetNameExt(), ".MW") == 0;
-		if (isMW && isDotMW) {
+
-			/* gotta be */
+		if (isMW && isDotMW) {
-			pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
+			/* gotta be */
-				ReformatHolder::kApplicYes,
+			pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
-				ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
+				ReformatHolder::kApplicYes,
-		} else if (isDotMW) {
+				ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
-			/* right type and name; maybe our test is broken? */
+		} else if (isDotMW) {
-			pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
+			/* right type and name; maybe our test is broken? */
-				ReformatHolder::kApplicProbably,
+			pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
-				ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
+				ReformatHolder::kApplicProbably,
-		} else if (isMW) {
+				ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
-			/* not likely, but offer it as non-default option */
+		} else if (isMW) {
-			pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
+			/* not likely, but offer it as non-default option */
-				ReformatHolder::kApplicProbablyNot,
+			pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
-				ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
+				ReformatHolder::kApplicProbablyNot,
-		} else {
+				ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
-			/* not one of ours */
+		} else {
-			pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
+			/* not one of ours */
-				ReformatHolder::kApplicNot,
+			pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
-				ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
+				ReformatHolder::kApplicNot,
-		}
+				ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
-	} else {
+		}
-		/* "unformatted" text even if ".MW"; nothing special required */
+	} else {
-		pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
+		/* "unformatted" text even if ".MW"; nothing special required */
-			ReformatHolder::kApplicNot,
+		pHolder->SetApplic(ReformatHolder::kReformatMagicWindow,
-			ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
+			ReformatHolder::kApplicNot,
-	}
+			ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
-}
+	}
-
+}
-/*
+
- * Figure out if this is a Magic Window "formatted" file.
+/*
- *
+ * Figure out if this is a Magic Window "formatted" file.
- * I don't know much about the format, so this is based on the similarities
+ *
- * observed between half a dozen documents from different sources.
+ * I don't know much about the format, so this is based on the similarities
- */
+ * observed between half a dozen documents from different sources.
-/*static*/ bool
+ */
-ReformatMagicWindow::IsFormatted(const ReformatHolder* pHolder)
+/*static*/ bool
-{
+ReformatMagicWindow::IsFormatted(const ReformatHolder* pHolder)
-	const unsigned char* ptr = pHolder->GetSourceBuf(ReformatHolder::kPartData);
+{
-	long srcLen = pHolder->GetSourceLen(ReformatHolder::kPartData);
+	const unsigned char* ptr = pHolder->GetSourceBuf(ReformatHolder::kPartData);
-	int i, count00, count20;
+	long srcLen = pHolder->GetSourceLen(ReformatHolder::kPartData);
-
+	int i, count00, count20;
-
+
-	/* want 256-byte header, plus a few bytes to check text */
+
-	if (srcLen < kHeaderLen+8)
+	/* want 256-byte header, plus a few bytes to check text */
-		return false;
+	if (srcLen < kHeaderLen+8)
-
+		return false;
-	/*
+
-	 * First byte always seems to be 0x8d.
+	/*
-	 */
+	 * First byte always seems to be 0x8d.
-	if (ptr[0x00] != 0x8d)
+	 */
-		return false;
+	if (ptr[0x00] != 0x8d)
-
+		return false;
-	/*
+
-	 * 0x58 - 0xa0 is mostly filled with 0x00 (for Magic Window) or 0x20
+	/*
-	 * (for Magic Window II).  Both seem to have space for the title in the
+	 * 0x58 - 0xa0 is mostly filled with 0x00 (for Magic Window) or 0x20
-	 * preceeding part, but it's high-ASCII for MW and low-ASCII for MW2.
+	 * (for Magic Window II).  Both seem to have space for the title in the
-	 *
+	 * preceeding part, but it's high-ASCII for MW and low-ASCII for MW2.
-	 * Expect 50 out of 72 to match.  If this is actually just uninitialized
+	 *
-	 * data then this test will be bogus.
+	 * Expect 50 out of 72 to match.  If this is actually just uninitialized
-	 */
+	 * data then this test will be bogus.
-	count00 = count20 = 0;
+	 */
-	for (i = 0x58; i < 0xa0; i++) {
+	count00 = count20 = 0;
-		if (ptr[i] == 0x00)
+	for (i = 0x58; i < 0xa0; i++) {
-			count00++;
+		if (ptr[i] == 0x00)
-		if (ptr[i] == 0x20)
+			count00++;
-			count20++;
+		if (ptr[i] == 0x20)
-	}
+			count20++;
-	if (count00 < 50 && count20 < 50)
+	}
-		return false;
+	if (count00 < 50 && count20 < 50)
-
+		return false;
-	/*
+
-	 * 0xa2 has some recognizeable bytes; sample values:
+	/*
-	 *	MW  42 06 36 50 08 40
+	 * 0xa2 has some recognizeable bytes; sample values:
-	 *	MW2 42 06 36 55 08 40
+	 *	MW  42 06 36 50 08 40
-	 *  MW2 42 04 3a 50 00 50
+	 *	MW2 42 06 36 55 08 40
-	 * Not really sure what to make of these.  If we can bracket these
+	 *  MW2 42 04 3a 50 00 50
-	 * values we might have something.
+	 * Not really sure what to make of these.  If we can bracket these
-	 */
+	 * values we might have something.
-	if (ptr[0xa2] != 0x42 ||
+	 */
-		(ptr[0xa3] < 2 && ptr[0xa3] > 10) ||
+	if (ptr[0xa2] != 0x42 ||
-		(ptr[0xa4] < 0x30 && ptr[0xa4] > 0x40))
+		(ptr[0xa3] < 2 && ptr[0xa3] > 10) ||
-		return false;
+		(ptr[0xa4] < 0x30 && ptr[0xa4] > 0x40))
-
+		return false;
-	/*
+
-	 * Make sure the rest of the file is 100% high ASCII.
+	/*
-	 */
+	 * Make sure the rest of the file is 100% high ASCII.
-	ptr += kHeaderLen;
+	 */
-	srcLen -= kHeaderLen;
+	ptr += kHeaderLen;
-	while (srcLen--) {
+	srcLen -= kHeaderLen;
-		if ((*ptr & 0x80) == 0)
+	while (srcLen--) {
-			return false;
+		if ((*ptr & 0x80) == 0)
-	}
+			return false;
-
+	}
-	return true;
+
-}
+	return true;
-
+}
-
+
-/*
+
- * Skip the header and text-convert the reset.
+/*
- */
+ * Skip the header and text-convert the rest.
-int
+ */
-ReformatMagicWindow::Process(const ReformatHolder* pHolder,
+int
-	ReformatHolder::ReformatID id, ReformatHolder::ReformatPart part,
+ReformatMagicWindow::Process(const ReformatHolder* pHolder,
-	ReformatOutput* pOutput)
+	ReformatHolder::ReformatID id, ReformatHolder::ReformatPart part,
-{
+	ReformatOutput* pOutput)
-	const unsigned char* srcPtr = pHolder->GetSourceBuf(part);
+{
-	long srcLen = pHolder->GetSourceLen(part);
+	const unsigned char* srcPtr = pHolder->GetSourceBuf(part);
-	long length = srcLen;
+	long srcLen = pHolder->GetSourceLen(part);
-	int retval = -1;
+	long length = srcLen;
-
+	int retval = -1;
-	fUseRTF = false;
+
-
+	fUseRTF = false;
-	RTFBegin();
+
-
+	RTFBegin();
-	if (srcLen <= kHeaderLen)
+
-		goto bail;
+	if (srcLen <= kHeaderLen)
-
+		goto bail;
-	ConvertEOL(srcPtr + kHeaderLen, srcLen - kHeaderLen, true);
+
-
+	ConvertEOL(srcPtr + kHeaderLen, srcLen - kHeaderLen, true);
-	//done:
+
-	RTFEnd();
+	//done:
-
+	RTFEnd();
-	SetResultBuffer(pOutput);
+
-	retval = 0;
+	SetResultBuffer(pOutput);
-
+	retval = 0;
-bail:
+
-	return retval;
+bail:
-}
+	return retval;
+}
+
+
+/*
+ * ===========================================================================
+ *		Gutenberg Word Processor
+ * ===========================================================================
+ */
+
+/*
+ * Decide whether or not we want to handle this file.
+ */
+void
+ReformatGutenberg::Examine(ReformatHolder* pHolder)
+{
+	if ((pHolder->GetFileType() == kTypeTXT)  && 
+		(pHolder->GetSourceFormat() == ReformatHolder::kSourceFormatGutenberg)) {
+
+		pHolder->SetApplic(ReformatHolder::kReformatGutenberg,
+			ReformatHolder::kApplicYes,
+			ReformatHolder::kApplicNot, ReformatHolder::kApplicNot);
+	}
+}
+
+
+/*
+ * Convert the text.
+ */
+int
+ReformatGutenberg::Process(const ReformatHolder* pHolder,
+	ReformatHolder::ReformatID id, ReformatHolder::ReformatPart part,
+	ReformatOutput* pOutput)
+{
+	const unsigned char* srcPtr = pHolder->GetSourceBuf(part);
+	long srcLen = pHolder->GetSourceLen(part);
+	long length = srcLen;
+	int retval = -1;
+
+	fUseRTF = false;
+
+	RTFBegin();
+
+	ConvertEOL(srcPtr, srcLen, true, true);
+
+	RTFEnd();
+
+	SetResultBuffer(pOutput);
+	retval = 0;
+
+	return retval;
+}

reformat/Text8.h

@@ -1,33 +1,49 @@
-/*
+/*
- * CiderPress
+ * CiderPress
- * Copyright (C) 2007 by faddenSoft, LLC.  All Rights Reserved.
+ * Copyright (C) 2009 by Ciderpress authors.  All Rights Reserved.
- * See the file LICENSE for distribution terms.
+ * Copyright (C) 2007 by faddenSoft, LLC.  All Rights Reserved.
- */
+ * See the file LICENSE for distribution terms.
-/*
+ */
- * Reformat 8-bit word processor files.
+/*
- */
+ * Reformat 8-bit word processor files.
-#ifndef __LR_TEXT8__
+ */
-#define __LR_TEXT8__
+#ifndef __LR_TEXT8__
-
+#define __LR_TEXT8__
-#include "ReformatBase.h"
+
-
+#include "ReformatBase.h"
-/*
+
- * Magic Window / Magic Window II
+/*
- */
+ * Magic Window / Magic Window II
-class ReformatMagicWindow : public ReformatText {
+ */
-public:
+class ReformatMagicWindow : public ReformatText {
-	ReformatMagicWindow(void) {}
+public:
-	virtual ~ReformatMagicWindow(void) {}
+	ReformatMagicWindow(void) {}
-
+	virtual ~ReformatMagicWindow(void) {}
-	virtual void Examine(ReformatHolder* pHolder);
+
-	virtual int Process(const ReformatHolder* pHolder,
+	virtual void Examine(ReformatHolder* pHolder);
-		ReformatHolder::ReformatID id, ReformatHolder::ReformatPart part,
+	virtual int Process(const ReformatHolder* pHolder,
-		ReformatOutput* pOutput);
+		ReformatHolder::ReformatID id, ReformatHolder::ReformatPart part,
-
+		ReformatOutput* pOutput);
-private:
+
-	static bool IsFormatted(const ReformatHolder* pHolder);
+private:
-
+	static bool IsFormatted(const ReformatHolder* pHolder);
-	enum { kHeaderLen = 256 };
+
-};
+	enum { kHeaderLen = 256 };
-
+};
-#endif /*__LR_TEXT8__*/
+
+/*
+ * Guterberg Word Processor
+ */
+class ReformatGutenberg : public ReformatText {
+public:
+	ReformatGutenberg(void) {}
+	virtual ~ReformatGutenberg(void) {}
+
+	virtual void Examine(ReformatHolder* pHolder);
+	virtual int Process(const ReformatHolder* pHolder,
+		ReformatHolder::ReformatID id, ReformatHolder::ReformatPart part,
+		ReformatOutput* pOutput);
+
+};
+
+#endif /*__LR_TEXT8__*/