Anyway, I wanted to share what I learned, so I wrote and commented a function to read all tags in a TIFF file and return them as formatted text. It reads the tags for all pages of multi-page TIFFs, and handles endian conversion. I could not fully test endian conversion, though, so I'd be happy to hear about any unusual results on platforms other than Windows.
NOTE: This code is free for any use at all, and is not released under any license in particular. I don't care if you copy it verbatim and pretend that you wrote it
Code: Select all
#LITTLE_ENDIAN = $4949
#BIG_ENDIAN = $4D4D
Macro SwapW(val)
(((val >> 8) & $00ff) | ((val << 8) & $ff00))
EndMacro
Macro SwapL(val)
(((val>>24) & $000000ff)|((val>>8) & $0000ff00)|((val<<8) & $00ff0000)|((val<<24) & $ff000000))
EndMacro
Procedure.s GetTIFFTags(filename$)
Protected result$, tiffile.l, ifd.l, tag.w, type.w
Protected nval.l, offset.l, fpos.l, byteorder.l
tiffile = ReadFile(#PB_Any, filename$)
byteorder = ReadWord(tiffile) ;check the endianness of the file
;prepare to handle reverse endianness depending on platform
SwapByteOrder.b = #False
CompilerSelect #PB_Compiler_OS
CompilerCase #PB_OS_AmigaOS
If byteorder = #LITTLE_ENDIAN : SwapByteOrder = #True : EndIf
CompilerCase #PB_OS_Linux
If byteorder = #LITTLE_ENDIAN : SwapByteOrder = #True : EndIf
CompilerCase #PB_OS_MacOS
If byteorder = #LITTLE_ENDIAN : SwapByteOrder = #True : EndIf
CompilerCase #PB_OS_Windows
If byteorder = #BIG_ENDIAN : SwapByteOrder = #True : EndIf
CompilerEndSelect
;position of 1st IFD is stored at offset 4 bytes
FileSeek(tiffile, 4)
ifd = ReadLong(tiffile)
If SwapByteOrder : ifd = SwapL(ifd) : EndIf
;we will support multi-page TIFF by looping through each IFD found in the file
While ifd
result$ = result$ + "TIFF directory at offset " + Str(ifd) + ":" + #CRLF$
;go to IFD
FileSeek(tiffile, ifd)
;1st 2 bytes of IFD indicate the # of tags stored
numtags = ReadWord(tiffile)
If SwapByteOrder : numtags = SwapW(numtags) : EndIf
;Enumerating the tags. The tag structure is simple:
; tag number: 2 bytes; unique identifier for each TIFF tag
; tag type: 2 bytes; indicates the type of value stored in the tag
; num values: 4 bytes; how many values of type 'tag type' are stored
; data offset: 4 bytes; offset (starting from 0) where the tag data is located.
; If the data is 4 bytes or less, the value is stored
; directly here instead of elsewhere to save time/space.
For t = 1 To numtags
tag = ReadWord(tiffile)
If SwapByteOrder : tag = SwapW(tag) : EndIf
result$ = result$ + " TAG " + Str(tag) + #TAB$
type = ReadWord(tiffile)
If SwapByteOrder : type = SwapW(type) : EndIf
Select type
Case 1 : result$ = result$ + "BYTE" + #TAB$
Case 2 : result$ = result$ + "CHAR" + #TAB$
Case 3 : result$ = result$ + "WORD" + #TAB$
Case 4 : result$ = result$ + "LONG" + #TAB$
Case 5 : result$ = result$ + "DOUBLE" + #TAB$
EndSelect
nval = ReadLong(tiffile)
If SwapByteOrder : nval = SwapL(nval) : EndIf
offset = ReadLong(tiffile) ;do not swap yet if different endianness - we will do it later
result$ = result$ + "value: "
fpos = Loc(tiffile) ;we will be visiting other offsets - we must store the current
;location so we can return here before moving on to the next tag.
Select type
Case 1 ;tag type is byte
If SwapByteOrder : offset = SwapL(offset) : EndIf
If nval <= 4
;value takes less than 4 bytes, so it is stored directly in offset.
;we must unpack each used byte as binary
For n = 0 To nval-1
result$ = result$ + Str(PeekB(@offset+n)) + " "
Next
Else
;value consumes more than 4 bytes; it is stored elsewhere
FileSeek(tiffile, offset)
For n = 0 To nval-1
result$ = result$ + Str(ReadByte(tiffile)) + " "
Next
FileSeek(tiffile, fpos)
EndIf
Case 2 ;type is char (1 byte)
If SwapByteOrder : offset = SwapL(offset) : EndIf
If nval <= 4
;value is stored in offset.
;unpack each used byte as char
For n = 0 To nval-1
result$ = result$ + Chr(PeekC(@offset+n))
Next
Else
;value consumes more than 4 bytes; it is stored elsewhere
FileSeek(tiffile, offset)
For n = 0 To nval-1
result$ = result$ + Chr(ReadCharacter(tiffile))
Next
FileSeek(tiffile, fpos)
EndIf
Case 3 ;type is word (2 bytes)
If nval <= 2
;value is stored in offset; unpack each used word
For n = 0 To nval-1 Step 2
valw.w = PeekW(@offset+n)
If SwapByteOrder : valw = SwapW(valw) : EndIf
result$ = result$ + Str(valw) + " "
Next
Else
If SwapByteOrder : offset = SwapL(offset) : EndIf
FileSeek(tiffile, offset)
For n = 0 To nval-1 Step 2
valw.w = ReadWord(tiffile)
If SwapByteOrder : valw = SwapW(valw) : EndIf
result$ = result$ + Str(val) + " "
Next
FileSeek(tiffile, fpos)
EndIf
Case 4 ;type is long (4 bytes)
If SwapByteOrder : offset = SwapL(offset) : EndIf
If nval = 1
;value can be taken directly from offset
result$ = result$ + Str(offset)
Else
FileSeek(tiffile, offset)
For n = 0 To nval-1
vall.l = ReadLong(tiffile)
If SwapByteOrder : vall = SwapL(vall) : EndIf
result$ = result$ + Str(val) + " "
Next
FileSeek(tiffile, fpos)
EndIf
Case 5 ;type is double (8 bytes)
;it is always more than 4 bytes, so seek to offset & read
If SwapByteOrder : offset = SwapL(offset) : EndIf
FileSeek(tiffile, offset)
For n = 0 To nval-1
;we will read the value in as two longs - the first is the
;numerator and the second is the denominator. the final result
;is the division of the numerator by the denominator; a float.
numer = ReadLong(tiffile)
If SwapByteOrder : numer = SwapL(numer) : EndIf
denom = ReadLong(tiffile)
If SwapByteOrder : denom = SwapL(denom) : EndIf
result$ = result$ + StrF(numer / denom, 2)
Next
FileSeek(tiffile, fpos)
EndSelect
result$ + #CRLF$
Next
result$ + #CRLF$ ;add some whitespace between IFDs for beauty;)
ifd = ReadLong(tiffile) ;0 if there are no more IFDs, else offset to next IFD
If SwapByteOrder : ifd = SwapL(ifd) : EndIf
Wend
CloseFile(tiffile)
ProcedureReturn result$
EndProcedure
