B/text: Text Template.

@Purpose: Code to support the text kind of value.
 
@-------------------------------------------------------------------------------

@p Block Format.
The short block for a text is two words long: the first word selects which
form of storage will be used to represent the content, and the second word
is a reference to that content. This reference is an I6 String or Routine
in all cases except one, when it's a pointer to a long block containing
a null-terminated array of characters, like a C string.

Clearly we need |PACKED_TEXT_STORAGE| and |UNPACKED_TEXT_STORAGE| to
distinguish between the two basic methods of text storage, roughly
equivalent to the pre-2013 kinds "text" and "indexed text". But why
do we need four?

|CONSTANT_PACKED_TEXT_STORAGE| is easy to explain: the BlkValue routines
normally detect constants using metadata in their long blocks, but of
course that won't work for values which haven't got any long blocks.
We use this instead. We don't need a |CONSTANT_UNPACKED_TEXT_STORAGE|
because I7 never compiles constant text in unpacked form.

The surprising one is |CONSTANT_PERISHABLE_TEXT_STORAGE|. This is a
constant created by the I7 compiler which is marked as being tricky
because its value is a text substitution containing references to local
variables. Unlike other text substitutions, this can't meaningfully be
stored away to be expanded later: it must be expanded into unpacked
text before it perishes.

@c
Constant CONSTANT_PACKED_TEXT_STORAGE     = BLK_BVBITMAP_TEXT + BLK_BVBITMAP_CONSTANT + 1;
Constant CONSTANT_PERISHABLE_TEXT_STORAGE = BLK_BVBITMAP_TEXT + BLK_BVBITMAP_CONSTANT + 2;
Constant PACKED_TEXT_STORAGE              = BLK_BVBITMAP_TEXT + 3;
Constant UNPACKED_TEXT_STORAGE            = BLK_BVBITMAP_TEXT + BLK_BVBITMAP_LONGBLOCK + 4;

@p Extent Of Long Block.
When there's a long block, we need enough of the entries to store the
number of characters, plus one for the null terminator.

@c
[ TEXT_TY_Extent arg1 x;
	x = BlkValueSeekZeroEntry(arg1);
	if (x < 0) return -1; ! should not happen, of course
	return x+1;
];

@p Character Set.
On the Z-machine, we use the 8-bit ZSCII character set, stored in bytes;
on Glulx, we use the opening 16-bit subset of Unicode (which though only a
subset covers almost all letter forms used on Earth), stored in half-words.

The Z-machine does have very partial Unicode support, but not in a way that
can help us here. It is capable of printing a wide range of Unicode
characters, and on a good interpreter with a good font (such as Zoom for Mac
OS X, using the Lucida Grande font) can produce many thousands of glyphs. But
it is not capable of printing those characters into memory rather than the
screen, an essential technique for texts: it can only write each character to
a single byte, and it does so in ZSCII. That forces our hand when it comes to
choosing the indexed-text character set.

@c
#IFDEF TARGET_ZCODE;
Constant TEXT_TY_Storage_Flags = BLK_FLAG_MULTIPLE;
Constant ZSCII_Tables;
#IFNOT;
Constant TEXT_TY_Storage_Flags = BLK_FLAG_MULTIPLE + BLK_FLAG_16_BIT;
Constant Large_Unicode_Tables;
#ENDIF;

{-segment:UnicodeData.i6t}
{-segment:Char.i6t}

@p KOV Support.
See the "BlockValues.i6t" segment for the specification of the following
routines. Because no block values are ever stored in a text, they can
freely be bitwise copied or forgotten, which is why we need do nothing
special to copy or destroy a text.

@c
[ TEXT_TY_Support task arg1 arg2 arg3;
	switch(task) {
		CREATE_KOVS:      return TEXT_TY_Create(arg2);
		CAST_KOVS:        TEXT_TY_Cast(arg1, arg2, arg3);
		MAKEMUTABLE_KOVS: return TEXT_TY_Mutable(arg1);
		COPYQUICK_KOVS:   rtrue;
		COPYSB_KOVS:	  TEXT_TY_CopySB(arg1, arg2);
		KINDDATA_KOVS:    return 0;
		EXTENT_KOVS:      return TEXT_TY_Extent(arg1);
		COMPARE_KOVS:     return TEXT_TY_Compare(arg1, arg2);
		READ_FILE_KOVS:   if (arg3 == -1) rtrue;
			              return TEXT_TY_ReadFile(arg1, arg2, arg3);
		WRITE_FILE_KOVS:  return TEXT_TY_WriteFile(arg1);
		HASH_KOVS:        return TEXT_TY_Hash(arg1);
		DEBUG_KOVS:       TEXT_TY_Debug(arg1);
	}
	! We choose not to respond to: DESTROY_KOVS, COPYKIND_KOVS, COPY_KOVS
	rfalse;
];

@p Debugging.
This shows the various forms a text's short block can take:

@c
[ TEXT_TY_Debug txt;
	switch (txt-->0) {
		CONSTANT_PACKED_TEXT_STORAGE:     print " = cp~", (PrintI6Text) txt-->1, "~";
		CONSTANT_PERISHABLE_TEXT_STORAGE: print " = cp~", (PrintI6Text) txt-->1, "~";
		PACKED_TEXT_STORAGE:              print " = p~", (PrintI6Text) txt-->1, "~";
		UNPACKED_TEXT_STORAGE:            print " = ~", (TEXT_TY_Say) txt, "~";
		default:                          print " broken?";
	}
];

@p Creation.
A newly created text is a two-word short block with no long block, like this:

	|Array ThisIsAText --> PACKED_TEXT_STORAGE EMPTY_TEXT_PACKED;|

@c
[ TEXT_TY_Create short_block x;
	return BlkValueCreateSB2(short_block, PACKED_TEXT_STORAGE, EMPTY_TEXT_PACKED);
];

@p Copy Short Block.
When a short block for a constant is copied, the new copy isn't a constant
any more.

@c
[ TEXT_TY_CopySB to_bv from_bv;
	BlkValueCopySB2(to_bv, from_bv);
	if (to_bv-->0 & BLK_BVBITMAP_CONSTANTMASK) to_bv-->0 = PACKED_TEXT_STORAGE;
];

@p Transmutation.
What happens if a text is stored in packed form, but we need to access or
change its individual characters? The answer is that we have to "transmute"
it into long block form. Sometimes this is a permanent change, but often
it's only temporary, and will soon be followed by an un-transmutation.

@c
[ TEXT_TY_Transmute txt;
	TEXT_TY_Temporarily_Transmute(txt);
];

[ TEXT_TY_Temporarily_Transmute txt  x;
	if ((txt) && (txt-->0 & BLK_BVBITMAP_LONGBLOCKMASK == 0)) {
		x = txt-->1; ! The old value was a packed string
		
		txt-->0 = UNPACKED_TEXT_STORAGE;
		txt-->1 = FlexAllocate(32, TEXT_TY, TEXT_TY_Storage_Flags);
		if (x ~= EMPTY_TEXT_PACKED) TEXT_TY_CastPrimitive(txt, false, x);
		
		return x;
	}
	return 0;
];

[ TEXT_TY_Untransmute txt pk cp x;
	if ((pk) && (txt-->0 == UNPACKED_TEXT_STORAGE)) {
		x = txt-->1; ! The old value was an unpacked string
		FlexFree(x);
		txt-->0 = cp;
		txt-->1 = pk; ! The value earlier returned by TEXT_TY_Temporarily_Transmute
	}
	return txt;
];

@p Mutability.
That neatly handles the question of how to make a text mutable. (Note that
constants are never created in unpacked form.)

@c
[ TEXT_TY_Mutable txt;
	if (txt-->0 & BLK_BVBITMAP_LONGBLOCKMASK == 0) {
		TEXT_TY_Transmute(txt);
		return 0;
	}
	return 2; ! Tell BlockValue there's a long block pointer
];

@p Casting.
In general computing, "casting" is the process of translating data in one
type into semantically equivalent data in another: the only interesting
cast here is that a snippet can be turned into a text.

@c
[ TEXT_TY_Cast to_txt from_kind from_value;
	if (from_kind == TEXT_TY) {
		BlkValueCopy(to_txt, from_value);
	} else if (from_kind == SNIPPET_TY) {
		TEXT_TY_Transmute(to_txt);
		TEXT_TY_CastPrimitive(to_txt, true, from_value);
	} else BlkValueError("impossible cast to text");
];

[ SNIPPET_TY_to_TEXT_TY to_txt snippet;
	return BlkValueCast(to_txt, SNIPPET_TY, snippet);
];

@p Data Conversion.
We use a single routine to handle two kinds of format translation: a
packed I6 string into an unpacked text, or a snippet into an unpacked text.

In each case, what we do is simply to print out the value we have, but with
the output stream set to memory rather than the screen. That gives us the
character by character version, neatly laid out in an array, and all we have
to do is to copy it into the text and add a null termination byte.

What complicates things is that the two virtual machines handle printing
to memory quite differently, and that the original text has unpredictable
length. We are going to try printing it into the array |TEXT_TY_Buffers|,
but what if the text is too big? Disastrously, the Z-machine simply
writes on in memory, corrupting all subsequent arrays and almost certainly
causing the story file to crash soon after. There is nothing we can do
to predict or avoid this, or to repair the damage: this is why the Inform
documentation warns users to be wary of using text with large
strings in the Z-machine, and advises the use of Glulx instead. Glulx
does handle overruns safely, and indeed allows us to dynamically allocate
memory as necessary so that we can always avoid overruns entirely.

In either case, though, it's useful to have |TEXT_TY_BufferSize|, the size
of the temporary buffer, large enough that it will never be overrun in
ordinary use. This is controllable with the use option "maximum indexed
text length".

@c
#ifndef TEXT_TY_BufferSize;
Constant TEXT_TY_BufferSize = 512;
#endif;
Constant TEXT_TY_NoBuffers = 2;

#ifdef TARGET_ZCODE;
Array TEXT_TY_Buffers -> TEXT_TY_BufferSize*TEXT_TY_NoBuffers; ! Where characters are bytes
#ifnot;
Array TEXT_TY_Buffers --> (TEXT_TY_BufferSize+2)*TEXT_TY_NoBuffers; ! Where characters are words
#endif;

Global RawBufferAddress = TEXT_TY_Buffers;
Global RawBufferSize = TEXT_TY_BufferSize;

Global TEXT_TY_CastPrimitiveNesting = 0;

@p Z Version.
The two versions of this routine, one for each virtual machine, are in all
important respects the same, but there are enough fiddly differences that
it's clearer to give two definitions, so:

@c
#ifdef TARGET_ZCODE;
[ TEXT_TY_CastPrimitive to_txt from_snippet from_value  len news buffer;
	if (to_txt == 0) BlkValueError("no destination for cast");
	SuspendRTP();
	buffer = RawBufferAddress + TEXT_TY_CastPrimitiveNesting*TEXT_TY_BufferSize;
	TEXT_TY_CastPrimitiveNesting++;
	if (TEXT_TY_CastPrimitiveNesting > TEXT_TY_NoBuffers)
		FlexError("ran out with too many simultaneous text conversions");

	@push say__p; @push say__pc;
	ClearParagraphing(6);
	@output_stream 3 buffer;
	if (from_value) {
		if (from_snippet) print (PrintSnippet) from_value;
		else print (PrintI6Text) from_value;
	}
	@output_stream -3;
	@pull say__pc; @pull say__p;
	ResumeRTP();

	len = buffer-->0;
	if (len > RawBufferSize-1) len = RawBufferSize-1;
	buffer->(len+2) = 0;

	TEXT_TY_CastPrimitiveNesting--;
	BlkValueMassCopyFromArray(to_txt, buffer+2, 1, len+1);
];

@p Glulx Version.

@c
#ifnot; ! TARGET_ZCODE
[ TEXT_TY_CastPrimitive to_txt from_snippet from_value
	len i stream saved_stream news buffer buffer_size memory_to_free results;

	if (to_txt == 0) BlkValueError("no destination for cast");

	buffer_size = (TEXT_TY_BufferSize + 2)*WORDSIZE;
	
	RawBufferSize = TEXT_TY_BufferSize;
	buffer = RawBufferAddress + TEXT_TY_CastPrimitiveNesting*buffer_size;
	TEXT_TY_CastPrimitiveNesting++;
	if (TEXT_TY_CastPrimitiveNesting > TEXT_TY_NoBuffers) {
		buffer = VM_AllocateMemory(buffer_size); memory_to_free = buffer;
		if (buffer == 0)
			FlexError("ran out with too many simultaneous text conversions");
	}

	if (unicode_gestalt_ok) {
		SuspendRTP();
		.RetryWithLargerBuffer;
		saved_stream = glk_stream_get_current();
		stream = glk_stream_open_memory_uni(buffer, RawBufferSize, filemode_Write, 0);
		glk_stream_set_current(stream);

		@push say__p; @push say__pc;
		ClearParagraphing(7);
		if (from_snippet) print (PrintSnippet) from_value;
		else print (PrintI6Text) from_value;
		@pull say__pc; @pull say__p;

		results = buffer + buffer_size - 2*WORDSIZE;
		glk_stream_close(stream, results);
		if (saved_stream) glk_stream_set_current(saved_stream);
		ResumeRTP();

		len = results-->1;
		if (len > RawBufferSize-1) {
			! Glulx had to truncate text output because the buffer ran out:
			! len is the number of characters which it tried to print
			news = RawBufferSize;
			while (news < len) news=news*2;
			i = VM_AllocateMemory(news*WORDSIZE);
			if (i ~= 0) {
				if (memory_to_free) VM_FreeMemory(memory_to_free);
				memory_to_free = i;
				buffer = i;
				RawBufferSize = news;
				buffer_size = (RawBufferSize + 2)*WORDSIZE;
				jump RetryWithLargerBuffer;
			}
			! Memory allocation refused: all we can do is to truncate the text
			len = RawBufferSize-1;
		}
		buffer-->(len) = 0;

		TEXT_TY_CastPrimitiveNesting--;
		BlkValueMassCopyFromArray(to_txt, buffer, 4, len+1);
	} else {
		RunTimeProblem(RTP_NOGLULXUNICODE);
	}
	if (memory_to_free) VM_FreeMemory(memory_to_free);
];
#endif; 

@p Comparison.
This is more or less |strcmp|, the traditional C library routine for comparing
strings, but it does pose a few interesting questions. The answers are:

(a) Two different unexpanded texts with substitutions are never equal, so
"[X]" and "[Y]" aren't equal as texts even if X and Y are equal.
(b) Otherwise we test the current value of the text as expanded, so "[X]"
and "17" can be equal as texts if X is 17.

@c
[ TEXT_TY_Compare left_txt right_txt rv;
	@push say__comp;
	say__comp = true;
	rv = TEXT_TY_Compare_Inner(left_txt, right_txt);
	@pull say__comp;
	return rv;
];

[ TEXT_TY_Compare_Inner left_txt right_txt
	pos ch1 ch2 capacity_left capacity_right fl fr cl cr cpl cpr;
	if (left_txt-->0 & BLK_BVBITMAP_LONGBLOCKMASK == 0) fl = true;
	if (right_txt-->0 & BLK_BVBITMAP_LONGBLOCKMASK == 0) fr = true;

	if (fl && fr) {
		if ((left_txt-->1 ofclass String) && (right_txt-->1 ofclass String))
			return left_txt-->1 - right_txt-->1;
		if ((left_txt-->1 ofclass Routine) && (right_txt-->1 ofclass Routine))
			return left_txt-->1 - right_txt-->1;
		cpl = left_txt-->0; cl = TEXT_TY_Temporarily_Transmute(left_txt);
		cpr = right_txt-->0; cr = TEXT_TY_Temporarily_Transmute(right_txt);		
	} else if (fl) {
		cpl = left_txt-->0; cl = TEXT_TY_Temporarily_Transmute(left_txt);
	} else if (fr) {
		cpr = right_txt-->0; cr = TEXT_TY_Temporarily_Transmute(right_txt);
	}
	if ((cl) || (cr)) {
		pos = TEXT_TY_Compare(left_txt, right_txt);
		TEXT_TY_Untransmute(left_txt, cl, cpl);
		TEXT_TY_Untransmute(right_txt, cr, cpr);
		return pos;
	}
	capacity_left = BlkValueLBCapacity(left_txt);
	capacity_right = BlkValueLBCapacity(right_txt);
	for (pos=0:(pos<capacity_left) && (pos<capacity_right):pos++) {
		ch1 = BlkValueRead(left_txt, pos);
		ch2 = BlkValueRead(right_txt, pos);
		if (ch1 ~= ch2) return ch1-ch2;
		if (ch1 == 0) return 0;
	}
	if (pos == capacity_left) return -1;
	return 1;
];

[ TEXT_TY_Distinguish left_txt right_txt;
	if (TEXT_TY_Compare(left_txt, right_txt) == 0) rfalse;
	rtrue;
];

@p Hashing.
This calculates a hash value for the string, using Bernstein's algorithm.

@c
[ TEXT_TY_Hash txt  rv len i p cp;
	cp = txt-->0; p = TEXT_TY_Temporarily_Transmute(txt);
	rv = 0;
	len = BlkValueLBCapacity(txt);
	for (i=0: i<len: i++)
		rv = rv * 33 + BlkValueRead(txt, i);
	TEXT_TY_Untransmute(txt, p, cp);
	return rv;
];

@p Printing.
Unicode is not the native character set on Glulx: it came along as a late
addition to Glulx's specification. The deal is that we have to explicitly
tell the Glk interface layer to perform certain operations in a Unicode way;
if we simply perform |print (char) ch;| then the character |ch| will be
printed in ZSCII rather than Unicode.

@c
[ TEXT_TY_Say txt  ch i dsize;
	if (txt==0) rfalse;
	if (txt-->0 & BLK_BVBITMAP_LONGBLOCKMASK == 0) return PrintI6Text(txt-->1);
	dsize = BlkValueLBCapacity(txt);
	for (i=0: i<dsize: i++) {
		ch = BlkValueRead(txt, i);
		if (ch == 0) break;
		#ifdef TARGET_ZCODE;
		print (char) ch;
		#ifnot; ! TARGET_ZCODE
		@streamunichar ch;
		#endif;
	}
	if (i == 0) rfalse;
	rtrue;
];

@p Capitalised printing.
It turns out to be useful to have a variation on this:

@c
[ TEXT_TY_Say_Capitalised txt mod rc;
	mod = BlkValueCreate(TEXT_TY);
	TEXT_TY_SubstitutedForm(mod, txt);
	if (TEXT_TY_CharacterLength(mod) > 0) {
		BlkValueWrite(mod, 0, CharToCase(BlkValueRead(mod, 0), 1));
		TEXT_TY_Say(mod);
		rc = true;
		say__p = 1;
	}
	BlkValueFree(mod);
	return rc;
];

@p Serialisation.
Here we print a serialised form of a text which can later be used
to reconstruct the original text. The printing is apparently to the screen,
but in fact always takes place when the output stream is a file.

The format chosen is a letter "S" for string, then a comma-separated list
of decimal character codes, ending with the null terminator, and followed by
a semicolon: thus |S65,66,67,0;| is the serialised form of the text "ABC".

@c
[ TEXT_TY_WriteFile txt len pos ch p cp;
	cp = txt-->0; p = TEXT_TY_Temporarily_Transmute(txt);
	len = BlkValueLBCapacity(txt);
	print "S";
	for (pos=0: pos<=len: pos++) {
		if (pos == len) ch = 0; else ch = BlkValueRead(txt, pos);
		if (ch == 0) {
			print "0;"; break;
		} else {
			print ch, ",";
		}
	}
	TEXT_TY_Untransmute(txt, p, cp);
];

@p Unserialisation.
If that's the word: the reverse process, in which we read a stream of
characters from a file and reconstruct the text which gave rise to
them.

@c
[ TEXT_TY_ReadFile txt auxf ch i v dg pos tsize p;
	TEXT_TY_Transmute(txt);
	tsize = BlkValueLBCapacity(txt);
	while (ch ~= 32 or 9 or 10 or 13 or 0 or -1) {
		ch = FileIO_GetC(auxf);
		if (ch == ',' or ';') {
			if (pos+1 >= tsize) {
				if (BlkValueSetLBCapacity(txt, 2*pos) == false) break;
				tsize = BlkValueLBCapacity(txt);
			}
			BlkValueWrite(txt, pos++, v);
			v = 0;
			if (ch == ';') break;
		} else {
			dg = ch - '0';
			v = v*10 + dg;
		}
	}
	BlkValueWrite(txt, pos, 0);
	return txt;
];

@p Substitution.

@c
[ TEXT_TY_SubstitutedForm to txt;
	if (txt) {
		BlkValueCopy(to, txt);
		TEXT_TY_Transmute(to);
	}
	return to;
];

[ TEXT_TY_IsSubstituted txt;
	if ((txt) &&
		(txt-->0 & BLK_BVBITMAP_LONGBLOCKMASK == 0) &&
		(txt-->1 ofclass Routine)) rfalse;
	rtrue;
];

@p Perishability.
As noted above, a perishable constant is one which must be expanded before
the values it refers to vanish from existence.

@c
[ TEXT_TY_ExpandIfPerishable to from;
	if ((from) && (from-->0 == CONSTANT_PERISHABLE_TEXT_STORAGE))
		return TEXT_TY_SubstitutedForm(to, from);
	return from;
];

@p Recognition-only-GPR.
An I6 general parsing routine to look at words from the position marker
|wn| in the player's command to see if they match the contents of the
text |txt|, returning either |GPR_PREPOSITION| or |GPR_FAIL|
according to whether a match could be made. This is used when the an
object's name is set to include one of its properties, and the property in
question is a text: "A flowerpot is a kind of thing. A flowerpot
has a text called pattern. Understand the pattern property as
describing a flowerpot." When the player types EXAMINE STRIPED FLOWERPOT,
and there is a flowerpot in scope, the following routine is called to
test whether its pattern property -- a text -- matches any words
at the position STRIPED FLOWERPOT. Assuming a pot does indeed have the
pattern "striped", the routine advances |wn| by 1 and returns
|GPR_PREPOSITION| to indicate a match.

This kind of GPR is called a "recognition-only-GPR", because it only
recognises an existing value: it doesn't parse a new one.

@c
[ TEXT_TY_ROGPR txt p cp r;
	if (txt == 0) return GPR_FAIL;
	cp = txt-->0; p = TEXT_TY_Temporarily_Transmute(txt);
	r = TEXT_TY_ROGPRI(txt);
	TEXT_TY_Untransmute(txt, p, cp);
	return r;
];
[ TEXT_TY_ROGPRI txt
	pos len wa wl wpos bdm ch own;
	bdm = true; own = wn;
	len = BlkValueLBCapacity(txt);
	for (pos=0: pos<=len: pos++) {
		if (pos == len) ch = 0; else ch = BlkValueRead(txt, pos);
		if (ch == 32 or 9 or 10 or 0) {
			if (bdm) continue;
			bdm = true;
			if (wpos ~= wl) return GPR_FAIL;
			if (ch == 0) break;
		} else {
			if (bdm) {
				bdm = false;
				if (NextWordStopped() == -1) return GPR_FAIL;
				wa = WordAddress(wn-1);
				wl = WordLength(wn-1);
				wpos = 0;
			}
			if (wa->wpos ~= ch or TEXT_TY_RevCase(ch)) return GPR_FAIL;
			wpos++;
		}
	}
	if (wn == own) return GPR_FAIL; ! Progress must be made to avoid looping
	return GPR_PREPOSITION;
];

@p Blobs.
That completes the compulsory services required for this KOV to function:
from here on, the remaining routines provide definitions of text-related
phrases in the Standard Rules.

What are the basic operations of text-handling? Clearly we want to be able
to search, and replace, but that is left for the segment "RegExp.i6t"
to handle. More basically we would like to be able to read and write
characters from the text. But texts in I7 tend to be of natural language,
rather than containing arbitrary material -- that's indeed why we call them
texts rather than strings. This means they are likely to be punctuated
sequences of words, divided up perhaps into sentences and even paragraphs.

So we provide facilities which regard a text as being an array of "blobs",
where a "blob" is a unit of text. The user can choose whether to see it
as an array of characters, or words (of three different sorts: see the
Inform documentation for details), or paragraphs, or lines. 

@c
Constant CHR_BLOB = 1; ! Construe as an array of characters
Constant WORD_BLOB = 2; ! Of words
Constant PWORD_BLOB = 3; ! Of punctuated words
Constant UWORD_BLOB = 4; ! Of unpunctuated words
Constant PARA_BLOB = 5; ! Of paragraphs
Constant LINE_BLOB = 6; ! Of lines

Constant REGEXP_BLOB = 7; ! Not a blob type as such, but needed as a distinct value

@p Blob Access.
The following routine runs a small finite-state-machine to count the number
of blobs in a text, using any of the above blob types (except
|REGEXP_BLOB|, which is used for other purposes). If the optional arguments
|ctxt| and |wanted| are supplied, it also copies the text of blob number
|wanted| (counting upwards from 1 at the start of the text) into the
text |ctxt|. If the further optional argument |rtxt| is supplied,
then |ctxt| is instead written with the original text |txt| as it would
read if the blob in question were replaced with the text in |rtxt|.

@c
Constant WS_BRM = 1;
Constant SKIPPED_BRM = 2;
Constant ACCEPTED_BRM = 3;
Constant ACCEPTEDP_BRM = 4;
Constant ACCEPTEDN_BRM = 5;
Constant ACCEPTEDPN_BRM = 6;

[ TEXT_TY_BlobAccess txt blobtype ctxt wanted rtxt
	p1 p2 cp1 cp2 r;
	if (txt==0) return 0;
	if (blobtype == CHR_BLOB) return TEXT_TY_CharacterLength(txt);
	cp1 = txt-->0; p1 = TEXT_TY_Temporarily_Transmute(txt);
	cp2 = rtxt-->0; p2 = TEXT_TY_Temporarily_Transmute(rtxt);
	TEXT_TY_Transmute(ctxt);
	r = TEXT_TY_BlobAccessI(txt, blobtype, ctxt, wanted, rtxt);
	TEXT_TY_Untransmute(txt, p1, cp1);
	TEXT_TY_Untransmute(rtxt, p2, cp2);
	return r;
];
[ TEXT_TY_BlobAccessI txt blobtype ctxt wanted rtxt
	brm oldbrm ch i dsize csize blobcount gp cl j;
	dsize = BlkValueLBCapacity(txt);
	if (ctxt) csize = BlkValueLBCapacity(ctxt);
	else if (rtxt) "*** rtxt without ctxt ***";
	brm = WS_BRM;
	for (i=0:i<dsize:i++) {
		ch = BlkValueRead(txt, i);
		if (ch == 0) break;
		oldbrm = brm;
		if (ch == 10 or 13 or 32 or 9) {
			if (oldbrm ~= WS_BRM) {
				gp = 0;
				for (j=i:j<dsize:j++) {
					ch = BlkValueRead(txt, j);
					if (ch == 0) { brm = WS_BRM; break; }
					if (ch == 10 or 13) { gp++; continue; }
					if (ch ~= 32 or 9) break;
				}
				ch = BlkValueRead(txt, i);
				if (j == dsize) brm = WS_BRM;
				switch (blobtype) {
					PARA_BLOB: if (gp >= 2) brm = WS_BRM;
					LINE_BLOB: if (gp >= 1) brm = WS_BRM;
					default: brm = WS_BRM;
				}
			}
		} else {
			gp = false;
			if ((blobtype == WORD_BLOB or PWORD_BLOB or UWORD_BLOB) &&
				(ch == '.' or ',' or '!' or '?'
						or '-' or '/' or '"' or ':' or ';'
						or '(' or ')' or '[' or ']' or '{' or '}'))
				gp = true;
			switch (oldbrm) {
				WS_BRM:
					brm = ACCEPTED_BRM;
					if (blobtype == WORD_BLOB) {
						if (gp) brm = SKIPPED_BRM;
					}
					if (blobtype == PWORD_BLOB) {
						if (gp) brm = ACCEPTEDP_BRM;
					}
				SKIPPED_BRM:
					if (blobtype == WORD_BLOB) {
						if (gp == false) brm = ACCEPTED_BRM;
					}
				ACCEPTED_BRM:
					if (blobtype == WORD_BLOB) {
						if (gp) brm = SKIPPED_BRM;
					}
					if (blobtype == PWORD_BLOB) {
						if (gp) brm = ACCEPTEDP_BRM;
					}
				ACCEPTEDP_BRM:
					if (blobtype == PWORD_BLOB) {
						if (gp == false) brm = ACCEPTED_BRM;
						else {
							if ((ch == BlkValueRead(txt, i-1)) &&
								(ch == '-' or '.')) blobcount--;
							blobcount++;
						}
					}
				ACCEPTEDN_BRM:
					if (blobtype == WORD_BLOB) {
						if (gp) brm = SKIPPED_BRM;
					}
					if (blobtype == PWORD_BLOB) {
						if (gp) brm = ACCEPTEDP_BRM;
					}
				ACCEPTEDPN_BRM:
					if (blobtype == PWORD_BLOB) {
						if (gp == false) brm = ACCEPTED_BRM;
						else {
							if ((ch == BlkValueRead(txt, i-1)) &&
								(ch == '-' or '.')) blobcount--;
							blobcount++;
						}
					}
			}
		}
		if (brm == ACCEPTED_BRM or ACCEPTEDP_BRM) {
			if (oldbrm ~= brm) blobcount++;
			if ((ctxt) && (blobcount == wanted)) {
				if (rtxt) {
					BlkValueWrite(ctxt, cl, 0);
					TEXT_TY_Concatenate(ctxt, rtxt, CHR_BLOB);
					csize = BlkValueLBCapacity(ctxt);
					cl = TEXT_TY_CharacterLength(ctxt);
					if (brm == ACCEPTED_BRM) brm = ACCEPTEDN_BRM;
					if (brm == ACCEPTEDP_BRM) brm = ACCEPTEDPN_BRM;
				} else {
					if (cl+1 >= csize) {
						if (BlkValueSetLBCapacity(ctxt, 2*cl) == false) break;
						csize = BlkValueLBCapacity(ctxt);
					}
					BlkValueWrite(ctxt, cl++, ch);
				}
			} else {
				if (rtxt) {
					if (cl+1 >= csize) {
						if (BlkValueSetLBCapacity(ctxt, 2*cl) == false) break;
						csize = BlkValueLBCapacity(ctxt);
					}
					BlkValueWrite(ctxt, cl++, ch);
				}
			}
		} else {
			if ((rtxt) && (brm ~= ACCEPTEDN_BRM or ACCEPTEDPN_BRM)) {
				if (cl+1 >= csize) {
					if (BlkValueSetLBCapacity(ctxt, 2*cl) == false) break;
					csize = BlkValueLBCapacity(ctxt);
				}
				BlkValueWrite(ctxt, cl++, ch);
			}
		}
	}
	if (ctxt) BlkValueWrite(ctxt, cl++, 0);
	return blobcount;
];

@p Get Blob.
The front end which uses the above routine to read a blob. (Note that, for
efficiency's sake, we read characters more directly.)

@c
[ TEXT_TY_GetBlob ctxt txt wanted blobtype;
	if (txt==0) return;
	if (blobtype == CHR_BLOB) return TEXT_TY_GetCharacter(ctxt, txt, wanted);
	TEXT_TY_BlobAccess(txt, blobtype, ctxt, wanted);
	return ctxt;
];

@p Replace Blob.
The front end which uses the above routine to replace a blob. (Once again,
characters are handled directly to avoid incurring all that overhead.)

@c
[ TEXT_TY_ReplaceBlob blobtype txt wanted rtxt ctxt ilen rlen i p cp;
	TEXT_TY_Transmute(txt);
	cp = rtxt-->0; p = TEXT_TY_Temporarily_Transmute(rtxt);
	if (blobtype == CHR_BLOB) {
		ilen = TEXT_TY_CharacterLength(txt);
		rlen = TEXT_TY_CharacterLength(rtxt);
		wanted--;
		if ((wanted >= 0) && (wanted<ilen)) {
			if (rlen == 1) {
				BlkValueWrite(txt, wanted, BlkValueRead(rtxt, 0));
			} else {
				ctxt = BlkValueCreate(TEXT_TY);
				TEXT_TY_Transmute(ctxt);
				if (BlkValueSetLBCapacity(ctxt, ilen+rlen+1)) {
					for (i=0:i<wanted:i++)
						BlkValueWrite(ctxt, i, BlkValueRead(txt, i));
					for (i=0:i<rlen:i++)
						BlkValueWrite(ctxt, wanted+i, BlkValueRead(rtxt, i));
					for (i=wanted+1:i<ilen:i++)
						BlkValueWrite(ctxt, rlen+i-1, BlkValueRead(txt, i));
					BlkValueWrite(ctxt, rlen+ilen, 0);
					BlkValueCopy(txt, ctxt);
				}
				BlkValueFree(ctxt);
			}
		}
	} else {
		ctxt = BlkValueCreate(TEXT_TY);
		TEXT_TY_BlobAccess(txt, blobtype, ctxt, wanted, rtxt);
		BlkValueCopy(txt, ctxt);
		BlkValueFree(ctxt);
	}
	TEXT_TY_Untransmute(rtxt, p, cp);
];

@p Replace Text.
This is the general routine which searches for any instance of |ftxt|,
as a blob, in |txt|, and replaces it with the text |rtxt|. It works on
any of the above blob-types, but two cases are special: first, if the
blob-type is |CHR_BLOB|, then it can do more than search and replace
for any instance of a single character: it can search and replace any
instance of a substring, so that |ftxt| is not required to be only a
single character. Second, if the blob-type is the special value
|REGEXP_BLOB| then |ftxt| is interpreted as a regular expression rather
than something literal to find: see "RegExp.i6t" for what happens next.

@c
[ TEXT_TY_ReplaceText blobtype txt ftxt rtxt
	r p1 p2 cp1 cp2;
	TEXT_TY_Transmute(txt);
	cp1 = ftxt-->0; p1 = TEXT_TY_Temporarily_Transmute(ftxt);
	cp2 = rtxt-->0; p2 = TEXT_TY_Temporarily_Transmute(rtxt);
	r = TEXT_TY_ReplaceTextI(blobtype, txt, ftxt, rtxt);
	TEXT_TY_Untransmute(ftxt, p1, cp1);
	TEXT_TY_Untransmute(rtxt, p2, cp2);
	return r;
];

[ TEXT_TY_ReplaceTextI blobtype txt ftxt rtxt
	ctxt csize ilen flen i cl mpos ch chm whitespace punctuation;
	if (blobtype == REGEXP_BLOB or CHR_BLOB) 
		return TEXT_TY_Replace_RE(blobtype, txt, ftxt, rtxt);
	
	ilen = TEXT_TY_CharacterLength(txt);
	flen = TEXT_TY_CharacterLength(ftxt);
	ctxt = BlkValueCreate(TEXT_TY);
	TEXT_TY_Transmute(ctxt);
	csize = BlkValueLBCapacity(ctxt);
	mpos = 0;

	whitespace = true; punctuation = false;
	for (i=0:i<=ilen:i++) {
		ch = BlkValueRead(txt, i);
		.MoreMatching;
		chm = BlkValueRead(ftxt, mpos++);
		if (mpos == 1) {
			switch (blobtype) {
				WORD_BLOB:
					if ((whitespace == false) && (punctuation == false)) chm = -1;
			}
		}
		whitespace = false;
		if (ch == 10 or 13 or 32 or 9) whitespace = true;
		punctuation = false;
		if (ch == '.' or ',' or '!' or '?'
			or '-' or '/' or '"' or ':' or ';'
			or '(' or ')' or '[' or ']' or '{' or '}') {
			if (blobtype == WORD_BLOB) chm = -1;
			punctuation = true;
		}
		if (ch == chm) {
			if (mpos == flen) {
				if (i == ilen) chm = 0;
				else chm = BlkValueRead(txt, i+1);
				if ((blobtype == CHR_BLOB) ||
					(chm == 0 or 10 or 13 or 32 or 9) ||
					(chm == '.' or ',' or '!' or '?'
						or '-' or '/' or '"' or ':' or ';'
						or '(' or ')' or '[' or ']' or '{' or '}')) {
					mpos = 0;
					cl = cl - (flen-1);
					BlkValueWrite(ctxt, cl, 0);
					TEXT_TY_Concatenate(ctxt, rtxt, CHR_BLOB);
					csize = BlkValueLBCapacity(ctxt);
					cl = TEXT_TY_CharacterLength(ctxt);
					continue;
				}
			}
		} else {
			mpos = 0;
		}
		if (cl+1 >= csize) {
			if (BlkValueSetLBCapacity(ctxt, 2*cl) == false) break;
			csize = BlkValueLBCapacity(ctxt);
		}
		BlkValueWrite(ctxt, cl++, ch);
	}
	BlkValueCopy(txt, ctxt);	
	BlkValueFree(ctxt);
];

@p Character Length.
When accessing at the character-by-character level, things are much easier
and we needn't go through any finite state machine palaver.

@c
[ TEXT_TY_CharacterLength txt ch i dsize p cp r;
	if (txt==0) return 0;
	cp = txt-->0; p = TEXT_TY_Temporarily_Transmute(txt);
	dsize = BlkValueLBCapacity(txt); r = dsize;
	for (i=0:i<dsize:i++) {
		ch = BlkValueRead(txt, i);
		if (ch == 0) { r = i; break; }
	}
	TEXT_TY_Untransmute(txt, p, cp);
	return r;
];

[ TEXT_TY_Empty txt;
	if (txt==0) rtrue;
	if (txt-->0 & BLK_BVBITMAP_LONGBLOCKMASK == 0) {
		if (txt-->1 == EMPTY_TEXT_PACKED) rtrue;
		rfalse;
	}
	if (TEXT_TY_CharacterLength(txt) == 0) rtrue;
	rfalse;
];

@p Get Character.
Characters in a text are numbered upwards from 1 by the users of this
routine: which is why we subtract 1 when reading the array in the
block-value, which counts from 0.

@c
[ TEXT_TY_GetCharacter ctxt txt i ch p cp;
	if (txt==0) return 0;
	cp = txt-->0; p = TEXT_TY_Temporarily_Transmute(txt);
	TEXT_TY_Transmute(ctxt);
	if ((i<=0) || (i>TEXT_TY_CharacterLength(txt))) ch = 0;
	else ch = BlkValueRead(txt, i-1);
	BlkValueWrite(ctxt, 0, ch);
	BlkValueWrite(ctxt, 1, 0);
	TEXT_TY_Untransmute(txt, p, cp);
	return ctxt;
];

@p Casing.
In many programming languages, characters are a distinct data type from
strings, but not in I7. To I7, a character is simply a text which
happens to have length 1 -- this has its inefficiencies, but is conceptually
easy for the user.

|TEXT_TY_CharactersOfCase(txt, case)| determines whether all the characters in |txt|
are letters of the given casing: 0 for lower case, 1 for upper case. In the
case of ZSCII, this is done correctly handling all of the European accented
letters; in the case of Unicode, it follows the Unicode standard.

Note that there is no requirement for |txt| to be only a single character
long.

@c
[ TEXT_TY_CharactersOfCase txt case i ch len p cp r;
	if (txt==0) return 0;
	cp = txt-->0; p = TEXT_TY_Temporarily_Transmute(txt);
	len = TEXT_TY_CharacterLength(txt);
	r = true;
	for (i=0:i<len:i++) {
		ch = BlkValueRead(txt, i);
		if ((ch) && (CharIsOfCase(ch, case) == false)) { r = false; break; }
	}
	TEXT_TY_Untransmute(txt, p, cp);
	return r;
];

@p Change Case.
We set |ctxt| to the text in |txt|, except that all the letters are
converted to the |case| given (0 for lower, 1 for upper). The definition
of what is a "letter", what case it has and what the other-case form is
are as specified in the ZSCII and Unicode standards.

@c
[ TEXT_TY_CharactersToCase ctxt txt case i ch len bnd pk cp;
	if (txt==0) return 0;
	cp = txt-->0; pk = TEXT_TY_Temporarily_Transmute(txt);
	TEXT_TY_Transmute(ctxt);
	len = TEXT_TY_CharacterLength(txt);
	if (BlkValueSetLBCapacity(ctxt, len+1)) {
		bnd = 1;
		for (i=0:i<len:i++) {
			ch = BlkValueRead(txt, i);
			if (case < 2) {
				BlkValueWrite(ctxt, i, CharToCase(ch, case));
			} else {
				BlkValueWrite(ctxt, i, CharToCase(ch, bnd));
				if (case == 2) {
					bnd = 0;
					if (ch == 0 or 10 or 13 or 32 or 9
						or '.' or ',' or '!' or '?'
						or '-' or '/' or '"' or ':' or ';'
						or '(' or ')' or '[' or ']' or '{' or '}') bnd = 1;
				}
				if (case == 3) {
					if (ch ~= 0 or 10 or 13 or 32 or 9) {
						if (bnd == 1) bnd = 0;
						else {
							if (ch == '.' or '!' or '?') bnd = 1;
						}
					}
				}
			}
		}
		BlkValueWrite(ctxt, len, 0);
	}
	TEXT_TY_Untransmute(txt, pk, cp);
	return ctxt;
];

@p Concatenation.
To concatenate two texts is to place one after the other: thus "green"
concatenated with "horn" makes "greenhorn". In this routine, |from_txt|
would be "horn", and is added at the end of |to_txt|, which is returned in
its expanded state.

When the blob type is |REGEXP_BLOB|, the routine is used not for simple
concatenation but to handle the concatenations occurring when a regular
expression search-and-replace is going on: see "RegExp.i6t".

@c
[ TEXT_TY_Concatenate to_txt from_txt blobtype ref_txt
	p cp r;
	if (to_txt==0) rfalse;
	if (from_txt==0) return to_txt;
	TEXT_TY_Transmute(to_txt);
	cp = from_txt-->0; p = TEXT_TY_Temporarily_Transmute(from_txt);
	r = TEXT_TY_ConcatenateI(to_txt, from_txt, blobtype, ref_txt);
	TEXT_TY_Untransmute(from_txt, p, cp);
	return r;
];

[ TEXT_TY_ConcatenateI to_txt from_txt blobtype ref_txt
	pos len ch i tosize x y case;
	switch(blobtype) {
		CHR_BLOB, 0:
			pos = TEXT_TY_CharacterLength(to_txt);
			len = TEXT_TY_CharacterLength(from_txt);
			if (BlkValueSetLBCapacity(to_txt, pos+len+1) == false) return to_txt;
			for (i=0:i<len:i++) {
				ch = BlkValueRead(from_txt, i);
				BlkValueWrite(to_txt, i+pos, ch);
			}
			BlkValueWrite(to_txt, len+pos, 0);
			return to_txt;
		REGEXP_BLOB:
			return TEXT_TY_RE_Concatenate(to_txt, from_txt, blobtype, ref_txt);
	}
	print "*** TEXT_TY_Concatenate used on impossible blob type ***^";
	rfalse;
];

@p Setting the Player's Command.
In effect, the text typed most recently by the player is a sort of
text already, though it isn't in text format, and doesn't live on
the heap.

@c
[ SetPlayersCommand from_txt i len at p cp;
	cp = from_txt-->0; p = TEXT_TY_Temporarily_Transmute(from_txt);
	len = TEXT_TY_CharacterLength(from_txt);
	if (len > 118) len = 118;
	#ifdef TARGET_ZCODE;
	buffer->1 = len; at = 2;
	#ifnot;
	buffer-->0 = len; at = 4;
	#endif;
	for (i=0:i<len:i++) buffer->(i+at) = CharToCase(BlkValueRead(from_txt, i), 0);
	for (:at+i<120:i++) buffer->(at+i) = ' ';
	VM_Tokenise(buffer, parse);
	players_command = 100 + WordCount(); ! The snippet variable "player's command"
	TEXT_TY_Untransmute(from_txt, p, cp);
];