Prep for 1.1.4 release.

Add ToUnicode map.
Drop the FEFF prefix on Unicode strings.
2025-07-13 14:34:28 +02:00 · 2023-12-03 16:55:57 -05:00 · 2023-11-19 20:49:30 -05:00 · 2023-11-19 07:30:17 -05:00 · 2023-11-19 07:06:35 -05:00 · 2023-11-18 22:15:52 -05:00
17 changed files with 589 additions and 167 deletions
--- a/.gitignore
+++ b/.gitignore
@ -13,4 +13,5 @@
 /pdfiototext
 /testpdfio
 /testpdfio-*.pdf
+/testttf
 /x64
--- a/CHANGES.md
+++ b/CHANGES.md
@ -2,6 +2,22 @@ Changes in PDFio
 ================


+v1.1.4 (December 3, 2023)
+-------------------------
+
+- Fixed detection of encrypted strings that are too short (Issue #52)
+- Fixed a TrueType CMAP decoding bug.
+- Fixed a text rendering issue for Asian text.
+- Added a ToUnicode map for Unicode text to support text copying.
+
+
+v1.1.3 (November 15, 2023)
+--------------------------
+
+- Fixed Unicode font support (Issue #16)
+- Fixed missing initializer for 40-bit RC4 encryption (Issue #51)
+
+
 v1.1.2 (October 10, 2023)
 -------------------------

--- a/15
+++ b/15
@ -29,7 +29,7 @@ DSONAME		=
 LDFLAGS		=
 LIBS		=	-lm -lz
 RANLIB		=	ranlib
-VERSION		=	1.1.2
+VERSION		=	1.1.4
 prefix		=	/usr/local


@ -67,12 +67,14 @@ LIBOBJS		=	\
 OBJS		=	\
 			$(LIBOBJS) \
 			pdfiototext.o \
-			testpdfio.o
+			testpdfio.o \
+			testttf.o
 TARGETS		=	\
 			$(DSONAME) \
 			libpdfio.a \
 			pdfiototext \
-			testpdfio
+			testpdfio \
+			testttf


 # Make everything
@ -136,6 +138,7 @@ install-shared:

 # Test everything
 test:	testpdfio
+	./testttf 2>test.log
 	./testpdfio 2>test.log

 valgrind:	testpdfio
@ -182,10 +185,16 @@ testpdfio:		testpdfio.o libpdfio.a
 	echo Linking $@...
 	$(CC) $(LDFLAGS) $(COMMONFLAGS) -o $@ testpdfio.o libpdfio.a $(LIBS)

+# TTF test program
+testttf:	ttf.o testttf.o
+	echo Linking $@...
+	$(CC) $(LDFLAGS) $(COMMONFLAGS) -o testttf ttf.o testttf.o $(LIBS)
+

 # Dependencies
 $(OBJS):		pdfio.h pdfio-private.h Makefile
 pdfio-content.o:	pdfio-content.h ttf.h
+testttf.o:		ttf.h
 ttf.o:			ttf.h

 # Make documentation using Codedoc <https://www.msweet.org/codedoc>
--- a/doc/pdfio.3
+++ b/doc/pdfio.3
@ -1,4 +1,4 @@
-.TH pdfio 3 "pdf read/write library" "2023-10-06" "pdf read/write library"
+.TH pdfio 3 "pdf read/write library" "2023-11-15" "pdf read/write library"
 .SH NAME
 pdfio \- pdf read/write library
 .SH Introduction
--- a/doc/pdfio.html
+++ b/doc/pdfio.html
@ -1,13 +1,13 @@
 <!DOCTYPE html>
 <html lang="en-US">
 <head>
-<title>PDFio Programming Manual v1.1.2</title>
+<title>PDFio Programming Manual v1.1.3</title>
 <meta http-equiv="Content-Type" content="text/html;charset=utf-8">
 <meta name="generator" content="codedoc v3.7">
 <meta name="author" content="Michael R Sweet">
 <meta name="language" content="en-US">
 <meta name="copyright" content="Copyright © 2021-2023 by Michael R Sweet">
-<meta name="version" content="1.1.2">
+<meta name="version" content="1.1.3">
 <style type="text/css"><!--
 body {
  background: white;
@ -245,7 +245,7 @@ span.string {
 <body>
 <div class="header">
 <p><img class="title" src="pdfio-512.png"></p>
-<h1 class="title">PDFio Programming Manual v1.1.2</h1>
+<h1 class="title">PDFio Programming Manual v1.1.3</h1>
 <p>Michael R Sweet</p>
 <p>Copyright © 2021-2023 by Michael R Sweet</p>
 </div>
--- a/pdfio-common.c
+++ b/pdfio-common.c
@ -375,9 +375,9 @@ _pdfioFileSeek(pdfio_file_t *pdf,	// I - PDF file
    if (whence != SEEK_END && offset >= pdf->bufpos && offset < (pdf->bufpos + pdf->bufend - pdf->buffer))
    {
      // Yes, seek within existing buffer...
-      pdf->bufptr = pdf->buffer + offset - pdf->bufpos;
+      pdf->bufptr = pdf->buffer + (offset - pdf->bufpos);
      PDFIO_DEBUG("_pdfioFileSeek: Seek within buffer, bufpos=%ld.\n", (long)pdf->bufpos);
-      PDFIO_DEBUG("_pdfioFileSeek: buffer=%p, bufptr=%p, bufend=%p\n", pdf->buffer, pdf->bufptr, pdf->bufend);
+      PDFIO_DEBUG("_pdfioFileSeek: buffer=%p, bufptr=%p(<%02X%02X...>), bufend=%p\n", pdf->buffer, pdf->bufptr, pdf->bufptr[0] & 255, pdf->bufptr[1] & 255, pdf->bufend);
      return (offset);
    }

--- a/pdfio-content.c
+++ b/pdfio-content.c
@ -1289,13 +1289,13 @@ pdfioFileCreateFontObjFromFile(
  pdfio_dict_t	*dict,			// Font dictionary
 		*desc,			// Font descriptor
 		*file;			// Font file dictionary
-  pdfio_obj_t	*obj,			// Font object
+  pdfio_obj_t	*obj = NULL,		// Font object
 		*desc_obj,		// Font descriptor object
 		*file_obj;		// Font file object
  const char	*basefont;		// Base font name
  pdfio_array_t	*bbox;			// Font bounding box array
  pdfio_stream_t *st;			// Font stream
-  int		fd;			// File
+  int		fd = -1;		// File
  unsigned char	buffer[16384];		// Read buffer
  ssize_t	bytes;			// Bytes read

@ -1324,48 +1324,32 @@ pdfioFileCreateFontObjFromFile(

  // Create the font file dictionary and object...
  if ((file = pdfioDictCreate(pdf)) == NULL)
-  {
-    ttfDelete(font);
-    close(fd);
-    return (NULL);
-  }
+    goto done;

  pdfioDictSetName(file, "Filter", "FlateDecode");

  if ((file_obj = pdfioFileCreateObj(pdf, file)) == NULL)
-  {
-    ttfDelete(font);
-    close(fd);
-    return (NULL);
-  }
+    goto done;

  if ((st = pdfioObjCreateStream(file_obj, PDFIO_FILTER_FLATE)) == NULL)
-  {
-    ttfDelete(font);
-    close(fd);
-    return (NULL);
-  }
+    goto done;

  while ((bytes = read(fd, buffer, sizeof(buffer))) > 0)
  {
    if (!pdfioStreamWrite(st, buffer, (size_t)bytes))
    {
-      ttfDelete(font);
-      close(fd);
      pdfioStreamClose(st);
-      return (NULL);
+      goto done;
    }
  }

  close(fd);
+  fd = -1;
  pdfioStreamClose(st);

  // Create the font descriptor dictionary and object...
  if ((bbox = pdfioArrayCreate(pdf)) == NULL)
-  {
-    ttfDelete(font);
-    return (NULL);
-  }
+    goto done;

  ttfGetBounds(font, &bounds);

@ -1375,10 +1359,7 @@ pdfioFileCreateFontObjFromFile(
  pdfioArrayAppendNumber(bbox, bounds.top);

  if ((desc = pdfioDictCreate(pdf)) == NULL)
-  {
-    ttfDelete(font);
-    return (NULL);
-  }
+    goto done;

  basefont = pdfioStringCreate(pdf, ttfGetPostScriptName(font));

@ -1397,56 +1378,65 @@ pdfioFileCreateFontObjFromFile(
  pdfioDictSetNumber(desc, "StemV", ttfGetWeight(font) / 4 + 25);

  if ((desc_obj = pdfioFileCreateObj(pdf, desc)) == NULL)
-  {
-    ttfDelete(font);
-    return (NULL);
-  }
+    goto done;

  pdfioObjClose(desc_obj);

  if (unicode)
  {
    // Unicode (CID) font...
-    pdfio_dict_t	*cid2gid;	// CIDToGIDMap dictionary
-    pdfio_obj_t		*cid2gid_obj;	// CIDToGIDMap object
+    pdfio_dict_t	*cid2gid,	// CIDToGIDMap dictionary
+			*to_unicode;	// ToUnicode dictionary
+    pdfio_obj_t		*cid2gid_obj,	// CIDToGIDMap object
+			*to_unicode_obj;// ToUnicode object
    size_t		i,		// Looping var
+			start,		// Start character
 			num_cmap;	// Number of CMap entries
    const int		*cmap;		// CMap entries
+    int			glyph,		// Current glyph
+			min_glyph,	// First glyph
+			max_glyph;	// Last glyph
+    unsigned short	glyphs[65536];	// Glyph to Unicode mapping
    unsigned char	*bufptr,	// Pointer into buffer
 			*bufend;	// End of buffer
    pdfio_dict_t	*type2;		// CIDFontType2 font dictionary
    pdfio_obj_t		*type2_obj;	// CIDFontType2 font object
    pdfio_array_t	*descendants;	// Decendant font list
    pdfio_dict_t	*sidict;	// CIDSystemInfo dictionary
+    pdfio_array_t	*w_array,	// Width array
+			*temp_array;	// Temporary width sub-array
+    int			w0, w1;		// Widths
+
+    // Create a CIDSystemInfo mapping to Adobe UCS2 v0 (Unicode)
+    if ((sidict = pdfioDictCreate(pdf)) == NULL)
+      goto done;
+
+    pdfioDictSetString(sidict, "Registry", "Adobe");
+    pdfioDictSetString(sidict, "Ordering", "Identity");
+    pdfioDictSetNumber(sidict, "Supplement", 0);

    // Create a CIDToGIDMap object for the Unicode font...
    if ((cid2gid = pdfioDictCreate(pdf)) == NULL)
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+      goto done;

 #ifndef DEBUG
    pdfioDictSetName(cid2gid, "Filter", "FlateDecode");
 #endif // !DEBUG

    if ((cid2gid_obj = pdfioFileCreateObj(pdf, cid2gid)) == NULL)
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+      goto done;

 #ifdef DEBUG
    if ((st = pdfioObjCreateStream(cid2gid_obj, PDFIO_FILTER_NONE)) == NULL)
 #else
    if ((st = pdfioObjCreateStream(cid2gid_obj, PDFIO_FILTER_FLATE)) == NULL)
 #endif // DEBUG
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+      goto done;

-    cmap = ttfGetCMap(font, &num_cmap);
+    cmap      = ttfGetCMap(font, &num_cmap);
+    min_glyph = 65536;
+    max_glyph = 0;
+    memset(glyphs, 0, sizeof(glyphs));

    PDFIO_DEBUG("pdfioFileCreateFontObjFromFile: num_cmap=%u\n", (unsigned)num_cmap);

@ -1464,6 +1454,12 @@ pdfioFileCreateFontObjFromFile(
        // Map to specified glyph...
        *bufptr++ = (unsigned char)(cmap[i] >> 8);
        *bufptr++ = (unsigned char)(cmap[i] & 255);
+
+        glyphs[cmap[i]] = i;
+        if (cmap[i] < min_glyph)
+          min_glyph = cmap[i];
+        if (cmap[i] > max_glyph)
+          max_glyph = cmap[i];
      }

      if (bufptr >= bufend)
@ -1472,8 +1468,7 @@ pdfioFileCreateFontObjFromFile(
        if (!pdfioStreamWrite(st, buffer, (size_t)(bufptr - buffer)))
        {
 	  pdfioStreamClose(st);
-          ttfDelete(font);
-          return (NULL);
+	  goto done;
        }

        bufptr = buffer;
@ -1486,30 +1481,102 @@ pdfioFileCreateFontObjFromFile(
      if (!pdfioStreamWrite(st, buffer, (size_t)(bufptr - buffer)))
      {
 	pdfioStreamClose(st);
-	ttfDelete(font);
-	return (NULL);
+	goto done;
      }
    }

    pdfioStreamClose(st);

+    // ToUnicode mapping object
+    to_unicode = pdfioDictCreate(pdf);
+    pdfioDictSetName(to_unicode, "Type", "CMap");
+    pdfioDictSetName(to_unicode, "CMapName", "Adobe-Identity-UCS2");
+    pdfioDictSetDict(to_unicode, "CIDSystemInfo", sidict);
+
+#ifndef DEBUG
+    pdfioDictSetName(to_unicode, "Filter", "FlateDecode");
+#endif // !DEBUG
+
+    if ((to_unicode_obj = pdfioFileCreateObj(pdf, to_unicode)) == NULL)
+      goto done;
+
+#ifdef DEBUG
+    if ((st = pdfioObjCreateStream(to_unicode_obj, PDFIO_FILTER_NONE)) == NULL)
+#else
+    if ((st = pdfioObjCreateStream(to_unicode_obj, PDFIO_FILTER_FLATE)) == NULL)
+#endif // DEBUG
+      goto done;
+
+    pdfioStreamPuts(st,
+		    "stream\n"
+		    "/CIDInit /ProcSet findresource begin\n"
+		    "12 dict begin\n"
+		    "begincmap\n"
+		    "/CIDSystemInfo<<\n"
+		    "/Registry (Adobe)\n"
+		    "/Ordering (UCS2)\n"
+		    "/Supplement 0\n"
+		    ">> def\n"
+		    "/CMapName /Adobe-Identity-UCS2 def\n"
+		    "/CMapType 2 def\n"
+		    "1 begincodespacerange\n"
+		    "<0000> <FFFF>\n"
+		    "endcodespacerange\n"
+		    "1 beginbfrange\n"
+		    "<0000> <FFFF> <0000>\n"
+                    "endbfrange\n"
+                    "endcmap\n"
+                    "CMapName currentdict /CMap defineresource pop\n"
+                    "end\n"
+                    "end\n");
+
+    pdfioStreamClose(st);
+
    // Create a CIDFontType2 dictionary for the Unicode font...
    if ((type2 = pdfioDictCreate(pdf)) == NULL)
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+      goto done;

-    if ((sidict = pdfioDictCreate(pdf)) == NULL)
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+    // Width array
+    if ((w_array = pdfioArrayCreate(pdf)) == NULL)
+      goto done;

-    // CIDSystemInfo mapping to Adobe UCS2 v0 (Unicode)
-    pdfioDictSetString(sidict, "Registry", "Adobe");
-    pdfioDictSetString(sidict, "Ordering", "Identity-H");
-    pdfioDictSetNumber(sidict, "Supplement", 0);
+    for (start = 0, w0 = ttfGetWidth(font, 0), i = 1; i < 65536; start = i, w0 = w1, i ++)
+    {
+      while (i < 65536 && (w1 = ttfGetWidth(font, i)) == w0)
+        i ++;
+
+      if ((i - start) > 1)
+      {
+        // Encode a repeating sequence...
+        pdfioArrayAppendNumber(w_array, start);
+        pdfioArrayAppendNumber(w_array, i - 1);
+        pdfioArrayAppendNumber(w_array, w0);
+      }
+      else
+      {
+        // Encode a non-repeating sequence...
+        pdfioArrayAppendNumber(w_array, start);
+
+        if ((temp_array = pdfioArrayCreate(pdf)) == NULL)
+	  goto done;
+
+        pdfioArrayAppendNumber(temp_array, w0);
+        for (w0 = w1, i ++; i < 65536; w0 = w1, i ++)
+        {
+          if ((w1 = ttfGetWidth(font, i)) == w0 && i < 65535)
+            break;
+
+	  pdfioArrayAppendNumber(temp_array, w0);
+        }
+
+        if (i == 65536)
+	  pdfioArrayAppendNumber(temp_array, w0);
+	else
+	  i --;
+
+        pdfioArrayAppendArray(w_array, temp_array);
+      }
+    }

    // Then the dictionary for the CID base font...
    pdfioDictSetName(type2, "Type", "Font");
@ -1518,56 +1585,41 @@ pdfioFileCreateFontObjFromFile(
    pdfioDictSetDict(type2, "CIDSystemInfo", sidict);
    pdfioDictSetObj(type2, "CIDToGIDMap", cid2gid_obj);
    pdfioDictSetObj(type2, "FontDescriptor", desc_obj);
+    pdfioDictSetArray(type2, "W", w_array);

    if ((type2_obj = pdfioFileCreateObj(pdf, type2)) == NULL)
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+      goto done;

    pdfioObjClose(type2_obj);

    // Create a Type 0 font object...
    if ((descendants = pdfioArrayCreate(pdf)) == NULL)
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+      goto done;

    pdfioArrayAppendObj(descendants, type2_obj);

    if ((dict = pdfioDictCreate(pdf)) == NULL)
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+      goto done;

    pdfioDictSetName(dict, "Type", "Font");
    pdfioDictSetName(dict, "Subtype", "Type0");
    pdfioDictSetName(dict, "BaseFont", basefont);
    pdfioDictSetArray(dict, "DescendantFonts", descendants);
    pdfioDictSetName(dict, "Encoding", "Identity-H");
+    pdfioDictSetObj(dict, "ToUnicode", to_unicode_obj);

-    if ((obj = pdfioFileCreateObj(pdf, dict)) == NULL)
-      return (NULL);
-
-    pdfioObjClose(obj);
+    if ((obj = pdfioFileCreateObj(pdf, dict)) != NULL)
+      pdfioObjClose(obj);
  }
  else
  {
    // Simple (CP1282 or custom encoding) 8-bit font...
    if (ttfGetMaxChar(font) >= 255 && !pdf->cp1252_obj && !create_cp1252(pdf))
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+      goto done;

    // Create a TrueType font object...
    if ((dict = pdfioDictCreate(pdf)) == NULL)
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
+      goto done;

    pdfioDictSetName(dict, "Type", "Font");
    pdfioDictSetName(dict, "Subtype", "TrueType");
@ -1577,15 +1629,15 @@ pdfioFileCreateFontObjFromFile(

    pdfioDictSetObj(dict, "FontDescriptor", desc_obj);

-    if ((obj = pdfioFileCreateObj(pdf, dict)) == NULL)
-    {
-      ttfDelete(font);
-      return (NULL);
-    }
-
-    pdfioObjClose(obj);
+    if ((obj = pdfioFileCreateObj(pdf, dict)) != NULL)
+      pdfioObjClose(obj);
  }

+  done:
+
+  if (fd >= 0)
+    close(fd);
+
  ttfDelete(font);

  return (obj);
@ -3000,7 +3052,7 @@ write_string(pdfio_stream_t *st,	// I - Stream


  // Start the string...
-  if (!pdfioStreamPuts(st, unicode ? "<FEFF" : "("))
+  if (!pdfioStreamPuts(st, unicode ? "<" : "("))
    return (false);

  // Loop through the string, handling UTF-8 as needed...
--- a/pdfio-crypto.c
+++ b/pdfio-crypto.c
@ -1,7 +1,7 @@
 //
 // Cryptographic support functions for PDFio.
 //
-// Copyright © 2021 by Michael R Sweet.
+// Copyright © 2021-2023 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@ -446,10 +446,18 @@ _pdfio_crypto_cb_t			// O  - Decryption callback or `NULL` for none

        // Initialize the RC4 context using 40 bits of the digest...
 	_pdfioCryptoRC4Init(&ctx->rc4, digest, 5);
+	*ivlen = 0;
 	return ((_pdfio_crypto_cb_t)_pdfioCryptoRC4Crypt);

-    case PDFIO_ENCRYPTION_RC4_128 :
    case PDFIO_ENCRYPTION_AES_128 :
+        if (*ivlen < 16)
+        {
+          *ivlen = 0;
+          _pdfioFileError(pdf, "Value too short for AES encryption.");
+          return (NULL);
+        }
+
+    case PDFIO_ENCRYPTION_RC4_128 :
 	// Copy the key data for the MD5 hash.
 	memcpy(data, pdf->file_key, sizeof(pdf->file_key));
 	data[16] = (uint8_t)obj->number;
--- a/pdfio-file.c
+++ b/pdfio-file.c
@ -1514,6 +1514,7 @@ load_obj_stream(pdfio_obj_t *obj)	// I - Object to load

    // Skip offset
    _pdfioTokenGet(&tb, buffer, sizeof(buffer));
+    PDFIO_DEBUG("load_obj_stream: %ld at offset %s\n", (long)number, buffer);
  }

  if (!buffer[0])
@ -1865,8 +1866,18 @@ load_xref(
 		break;
 	    }

-	    if (i >= num_sobjs && num_sobjs < (sizeof(sobjs) / sizeof(sobjs[0])))
-	      sobjs[num_sobjs ++] = (size_t)offset;
+	    if (i >= num_sobjs)
+	    {
+	      if (num_sobjs < (sizeof(sobjs) / sizeof(sobjs[0])))
+	      {
+		sobjs[num_sobjs ++] = (size_t)offset;
+	      }
+	      else
+	      {
+		_pdfioFileError(pdf, "Too many object streams.");
+	        return (false);
+	      }
+	    }
 	  }
 	  else if (!current)
 	  {
--- a/pdfio-stream.c
+++ b/pdfio-stream.c
@ -452,6 +452,7 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
      return (NULL);
    }

+    PDFIO_DEBUG("_pdfioStreamOpen: ivlen=%d\n", (int)ivlen);
    if (ivlen > 0)
      _pdfioFileConsume(st->pdf, ivlen);

@ -567,6 +568,7 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
      else
        st->predictor = _PDFIO_PREDICTOR_NONE;

+      PDFIO_DEBUG("_pdfioStreamOpen: pos=%ld\n", (long)_pdfioFileTell(st->pdf));
      if (sizeof(st->cbuffer) > st->remaining)
 	rbytes = _pdfioFileRead(st->pdf, st->cbuffer, st->remaining);
      else
--- a/pdfio-value.c
+++ b/pdfio-value.c
@ -383,7 +383,10 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
 	return (false);
      }

-      cb      = _pdfioCryptoMakeReader(pdf, obj, &ctx, v->value.binary.data, &ivlen);
+      ivlen = v->value.binary.datalen;
+      if ((cb = _pdfioCryptoMakeReader(pdf, obj, &ctx, v->value.binary.data, &ivlen)) == NULL)
+	return (false);
+
      templen = (cb)(&ctx, temp, v->value.binary.data + ivlen, v->value.binary.datalen - ivlen);

      // Copy the decrypted string back to the value and adjust the length...
--- a/pdfio.h
+++ b/pdfio.h
@ -23,7 +23,7 @@ extern "C" {
 // Version number...
 //

-#  define PDFIO_VERSION		"1.1.2"
+#  define PDFIO_VERSION		"1.1.4"


 //
--- a/pdfio_native.nuspec
+++ b/pdfio_native.nuspec
@ -3,7 +3,7 @@
    <metadata>
        <id>pdfio_native</id>
        <title>PDFio Library for VS2019+</title>
-        <version>1.1.2</version>
+        <version>1.1.4</version>
        <authors>Michael R Sweet</authors>
        <owners>michaelrsweet</owners>
        <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>
@ -16,7 +16,7 @@
        <copyright>Copyright © 2019-2023 by Michael R Sweet</copyright>
        <tags>pdf file native</tags>
 	<dependencies>
-	    <dependency id="pdfio_native.redist" version="1.1.2" />
+	    <dependency id="pdfio_native.redist" version="1.1.4" />
 	    <dependency id="zlib_native.redist" version="1.2.11" />
 	</dependencies>
    </metadata>
--- a/pdfio_native.redist.nuspec
+++ b/pdfio_native.redist.nuspec
@ -3,7 +3,7 @@
    <metadata>
        <id>pdfio_native.redist</id>
        <title>PDFio Library for VS2019+</title>
-        <version>1.1.2</version>
+        <version>1.1.4</version>
        <authors>Michael R Sweet</authors>
        <owners>michaelrsweet</owners>
        <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>
--- a/testpdfio.c
+++ b/testpdfio.c
@ -44,7 +44,7 @@ static int	verify_image(pdfio_file_t *pdf, size_t number);
 static int	write_alpha_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font);
 static int	write_color_patch(pdfio_stream_t *st, bool device);
 static int	write_color_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font);
-static int	write_font_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font, bool unicode);
+static int	write_font_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font, const char *textfontfile, bool unicode);
 static int	write_header_footer(pdfio_stream_t *st, const char *title, int number);
 static pdfio_obj_t *write_image_object(pdfio_file_t *pdf, _pdfio_predictor_t predictor);
 static int	write_images_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font);
@ -455,7 +455,7 @@ do_test_file(const char *filename,	// I - PDF filename
 	      }
 	    }

-	    printf("    Page #%d is %gx%g.\n", (int)n + 1, media_box.x2, media_box.y2);
+	    printf("    Page #%d (obj %d) is %gx%g.\n", (int)n + 1, (int)pdfioObjGetNumber(obj), media_box.x2, media_box.y2);
 	  }
 	}

@ -2229,14 +2229,19 @@ write_color_test(pdfio_file_t *pdf,	// I - PDF file
 //

 static int				// O - 1 on failure, 0 on success
-write_font_test(pdfio_file_t *pdf,	// I - PDF file
-                int          number,	// I - Page number
-		pdfio_obj_t  *font,	// I - Page number font
-		bool         unicode)	// I - Use Unicode font?
+write_font_test(
+    pdfio_file_t *pdf,			// I - PDF file
+    int          number,		// I - Page number
+    pdfio_obj_t  *font,			// I - Page number font
+    const char   *textfontfile,		// I - Text font file
+    bool         unicode)		// I - Use Unicode font?
 {
  pdfio_dict_t		*dict;		// Page dictionary
  pdfio_stream_t	*st;		// Page contents stream
-  pdfio_obj_t		*opensans;	// OpenSans-Regular font
+  pdfio_obj_t		*textfont;	// Text font
+  char			title[256],	// Page title
+			textname[256],	// Name of text font
+			*ptr;		// Pointer into name
  int			i;		// Looping var
  static const char * const welcomes[] =// "Welcome" in many languages
  {
@ -2387,28 +2392,16 @@ write_font_test(pdfio_file_t *pdf,	// I - PDF file
    "Märr-ŋamathirri",
    "Ẹ ku abọ",
    "Kíimak 'oolal",
-    "Ngiyakwemukela"
+    "Ngiyakwemukela",
+    "いらっしゃいませ"
  };


-#if 0
-  if (unicode)
-  {
-    fputs("pdfioFileCreateFontObjFromFile(NotoSansJP-Regular.otf): ", stdout);
-    if ((opensans = pdfioFileCreateFontObjFromFile(pdf, "testfiles/NotoSansJP-Regular.otf", true)) != NULL)
-      puts("PASS");
-    else
-      return (1);
-  }
+  printf("pdfioFileCreateFontObjFromFile(%s): ", textfontfile);
+  if ((textfont = pdfioFileCreateFontObjFromFile(pdf, textfontfile, unicode)) != NULL)
+    puts("PASS");
  else
-#endif // 0
-  {
-    fputs("pdfioFileCreateFontObjFromFile(OpenSans-Regular.ttf): ", stdout);
-    if ((opensans = pdfioFileCreateFontObjFromFile(pdf, "testfiles/OpenSans-Regular.ttf", unicode)) != NULL)
-      puts("PASS");
-    else
-      return (1);
-  }
+    return (1);

  fputs("pdfioDictCreate: ", stdout);
  if ((dict = pdfioDictCreate(pdf)) != NULL)
@ -2423,7 +2416,7 @@ write_font_test(pdfio_file_t *pdf,	// I - PDF file
    return (1);

  fputs("pdfioPageDictAddFont(F2): ", stdout);
-  if (pdfioPageDictAddFont(dict, "F2", opensans))
+  if (pdfioPageDictAddFont(dict, "F2", textfont))
    puts("PASS");
  else
    return (1);
@ -2435,7 +2428,21 @@ write_font_test(pdfio_file_t *pdf,	// I - PDF file
  else
    return (1);

-  if (write_header_footer(st, unicode ? "Unicode TrueType Font Test" : "CP1252 TrueType Font Test", number))
+  if ((ptr = strrchr(textfontfile, '/')) != NULL)
+    strncpy(textname, ptr + 1, sizeof(textname) - 1);
+  else
+    strncpy(textname, textfontfile, sizeof(textname) - 1);
+
+  textname[sizeof(textname) - 1] = '\0';
+  if ((ptr = strrchr(textname, '.')) != NULL)
+    *ptr = '\0';
+
+  if (unicode)
+    snprintf(title, sizeof(title), "Unicode %s Font Test", textname);
+  else
+    snprintf(title, sizeof(title), "CP1252 %s Font Test", textname);
+
+  if (write_header_footer(st, title, number))
    goto error;

  fputs("pdfioContentTextBegin(): ", stdout);
@ -3390,14 +3397,17 @@ write_unit_file(
    return (1);

  // Test TrueType fonts...
-  if (write_font_test(outpdf, 9, helvetica, false))
+  if (write_font_test(outpdf, 9, helvetica, "testfiles/OpenSans-Regular.ttf", false))
    return (1);

-  if (write_font_test(outpdf, 10, helvetica, true))
+  if (write_font_test(outpdf, 10, helvetica, "testfiles/OpenSans-Regular.ttf", true))
+    return (1);
+
+  if (write_font_test(outpdf, 11, helvetica, "testfiles/NotoSansJP-Regular.otf", true))
    return (1);

  // Print this text file...
-  if (write_text_test(outpdf, 11, helvetica, "README.md"))
+  if (write_text_test(outpdf, 12, helvetica, "README.md"))
    return (1);

  fputs("pdfioFileGetNumPages: ", stdout);
--- a/testttf.c
+++ b/testttf.c
@ -0,0 +1,304 @@
+//
+// Unit test program for TTF library
+//
+//     https://github.com/michaelrsweet/ttf
+//
+// Copyright © 2018-2023 by Michael R Sweet.
+//
+// Licensed under Apache License v2.0.  See the file "LICENSE" for more
+// information.
+//
+// Usage:
+//
+//   ./testttf [FILENAME]
+//
+
+#include <stdio.h>
+#include "ttf.h"
+
+
+//
+// Local functions...
+//
+
+static void	error_cb(void *data, const char *message);
+static int	test_font(const char *filename);
+
+
+//
+// 'main()' - Main entry for unit tests.
+//
+
+int					// O - Exit status
+main(int  argc,				// I - Number of command-line arguments
+     char *argv[])			// I - Command-line arguments
+{
+  int		i;			// Looping var
+  int		errors = 0;		// Number of errors
+
+
+  if (argc > 1)
+  {
+    for (i = 1; i < argc; i ++)
+      errors += test_font(argv[i]);
+  }
+  else
+  {
+    // Test with the bundled TrueType files...
+    errors += test_font("testfiles/OpenSans-Bold.ttf");
+    errors += test_font("testfiles/OpenSans-Regular.ttf");
+    errors += test_font("testfiles/NotoSansJP-Regular.otf");
+  }
+
+  if (!errors)
+    puts("\nALL TESTS PASSED");
+  else
+    printf("\n%d TEST(S) FAILED\n", errors);
+
+  return (errors);
+}
+
+
+//
+// 'error_cb()' - Error callback.
+//
+
+static void
+error_cb(void       *data,		// I - User data (not used)
+         const char *message)		// I - Message string
+{
+  fprintf(stderr, "FAIL (%s)\n", message);
+}
+
+
+//
+// 'test_font()' - Test a font file.
+//
+
+static int				// O - Number of errors
+test_font(const char *filename)		// I - Font filename
+{
+  int		i,			// Looping var
+		errors = 0;		// Number of errors
+  ttf_t		*font;			// Font
+  const char	*value;			// Font (string) value
+  int		intvalue;		// Font (integer) value
+  float		realvalue;		// Font (real) value
+  ttf_rect_t	bounds;			// Bounds
+  ttf_rect_t	extents;		// Extents
+  size_t	num_fonts;		// Number of fonts
+  ttf_style_t	style;			// Font style
+  ttf_weight_t	weight;			// Font weight
+  static const char * const stretches[] =
+  {					// Font stretch strings
+    "TTF_STRETCH_NORMAL",		// normal
+    "TTF_STRETCH_ULTRA_CONDENSED",	// ultra-condensed
+    "TTF_STRETCH_EXTRA_CONDENSED",	// extra-condensed
+    "TTF_STRETCH_CONDENSED",		// condensed
+    "TTF_STRETCH_SEMI_CONDENSED",	// semi-condensed
+    "TTF_STRETCH_SEMI_EXPANDED",	// semi-expanded
+    "TTF_STRETCH_EXPANDED",		// expanded
+    "TTF_STRETCH_EXTRA_EXPANDED",	// extra-expanded
+    "TTF_STRETCH_ULTRA_EXPANDED"	// ultra-expanded
+  };
+  static const char * const strings[] =	// Test strings
+  {
+    "Hello, World!",			// English
+    "مرحبا بالعالم!",			// Arabic
+    "Bonjour le monde!",		// French
+    "Γειά σου Κόσμε!",			// Greek
+    "שלום עולם!",			// Hebrew
+    "Привет мир!",			// Russian
+    "こんにちは世界！"			// Japanese
+  };
+  static const char * const styles[] =	// Font style names
+  {
+    "TTF_STYLE_NORMAL",
+    "TTF_STYLE_ITALIC",
+    "TTF_STYLE_OBLIQUE"
+  };
+
+
+  printf("ttfCreate(\"%s\"): ", filename);
+  if ((font = ttfCreate(filename, 0, error_cb, NULL)) != NULL)
+    puts("PASS");
+  else
+    errors ++;
+
+  fputs("ttfGetAscent: ", stdout);
+  if ((intvalue = ttfGetAscent(font)) > 0)
+  {
+    printf("PASS (%d)\n", intvalue);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetBounds: ", stdout);
+  if (ttfGetBounds(font, &bounds))
+  {
+    printf("PASS (%g %g %g %g)\n", bounds.left, bounds.bottom, bounds.right, bounds.top);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetCapHeight: ", stdout);
+  if ((intvalue = ttfGetCapHeight(font)) > 0)
+  {
+    printf("PASS (%d)\n", intvalue);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetCopyright: ", stdout);
+  if ((value = ttfGetCopyright(font)) != NULL)
+  {
+    printf("PASS (%s)\n", value);
+  }
+  else
+  {
+    puts("WARNING (no copyright found)");
+  }
+
+  for (i = 0; i < (int)(sizeof(strings) / sizeof(strings[0])); i ++)
+  {
+    printf("ttfGetExtents(\"%s\"): ", strings[i]);
+    if (ttfGetExtents(font, 12.0f, strings[i], &extents))
+    {
+      printf("PASS (%.1f %.1f %.1f %.1f)\n", extents.left, extents.bottom, extents.right, extents.top);
+    }
+    else
+    {
+      puts("FAIL");
+      errors ++;
+    }
+  }
+
+  fputs("ttfGetFamily: ", stdout);
+  if ((value = ttfGetFamily(font)) != NULL)
+  {
+    printf("PASS (%s)\n", value);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetItalicAngle: ", stdout);
+  if ((realvalue = ttfGetItalicAngle(font)) >= -180.0 && realvalue <= 180.0)
+  {
+    printf("PASS (%g)\n", realvalue);
+  }
+  else
+  {
+    printf("FAIL (%g)\n", realvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetNumFonts: ", stdout);
+  if ((num_fonts = ttfGetNumFonts(font)) > 0)
+  {
+    printf("PASS (%u)\n", (unsigned)num_fonts);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetPostScriptName: ", stdout);
+  if ((value = ttfGetPostScriptName(font)) != NULL)
+  {
+    printf("PASS (%s)\n", value);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetStretch: ", stdout);
+  if ((intvalue = (int)ttfGetStretch(font)) >= TTF_STRETCH_NORMAL && intvalue <= TTF_STRETCH_ULTRA_EXPANDED)
+  {
+    printf("PASS (%s)\n", stretches[intvalue]);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetStyle: ", stdout);
+  if ((style = ttfGetStyle(font)) >= TTF_STYLE_NORMAL && style <= TTF_STYLE_ITALIC)
+  {
+    printf("PASS (%s)\n", styles[style]);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetVersion: ", stdout);
+  if ((value = ttfGetVersion(font)) != NULL)
+  {
+    printf("PASS (%s)\n", value);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetWeight: ", stdout);
+  if ((weight = ttfGetWeight(font)) >= 0)
+  {
+    printf("PASS (%u)\n", (unsigned)weight);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetWidth(' '): ", stdout);
+  if ((intvalue = ttfGetWidth(font, ' ')) > 0)
+  {
+    printf("PASS (%d)\n", intvalue);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetXHeight: ", stdout);
+  if ((intvalue = ttfGetXHeight(font)) > 0)
+  {
+    printf("PASS (%d)\n", intvalue);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfIsFixedPitch: ", stdout);
+  if (ttfIsFixedPitch(font))
+    puts("PASS (true)");
+  else
+    puts("PASS (false)");
+
+  ttfDelete(font);
+
+  return (errors);
+}
--- a/ttf.c
+++ b/ttf.c
@ -71,7 +71,7 @@ typedef __int64 ssize_t;		// POSIX type not present on Windows...


 //
-// DEBUG is typically defined for debug builds.  TTF_DEBUG maps to printf when
+// DEBUG is typically defined for debug builds.  TTF_DEBUG maps to fprintf when
 // DEBUG is defined and is a no-op otherwise...
 //

@ -448,7 +448,7 @@ ttfCreate(const char   *filename,	// I - Filename
    font->cap_height = font->ascent;

  if (font->x_height == 0)
-    font->x_height   = 3 * font->ascent / 5;
+    font->x_height = 3 * font->ascent / 5;

  // Build a sparse glyph widths table...
  font->min_char = -1;
@ -477,6 +477,11 @@ ttfCreate(const char   *filename,	// I - Filename
      else
 	font->widths[bin][i & 255] = widths[glyph];
    }
+
+#ifdef DEBUG
+    if (i >= ' ' && i < 127 && font->widths[0])
+      TTF_DEBUG("ttfCreate: width['%c']=%d(%d)\n", (char)i, font->widths[0][i].width, font->widths[0][i].left_bearing);
+#endif // DEBUG
  }

  // Cleanup and return the font...
@ -687,9 +692,6 @@ ttfGetExtents(
      ch = *s++;
    }

-    // Issue #1: Offset past ".notdef"...
-    ch ++;
-
    // Find its width...
    if ((widths = font->widths[ch / 256]) != NULL)
    {
@ -736,17 +738,6 @@ ttfGetFamily(ttf_t *font)		// I - Font
 }


-//
-// 'ttfIsFixedPitch()' - Determine whether a font is fixedpitch.
-//
-
-bool					// O - `true` if fixed pitch, `false` otherwise
-ttfIsFixedPitch(ttf_t *font)		// I - Font
-{
-  return (font ? font->is_fixed : false);
-}
-
-
 //
 // 'ttfGetItalicAngle()' - Get the italic angle.
 //
@ -855,13 +846,14 @@ int					// O - Width in 1000ths
 ttfGetWidth(ttf_t *font,		// I - Font
            int   ch)			// I - Unicode character
 {
-  int	bin = ch >> 8;			// Bin in widths array
+  int	bin =  ch >> 8;			// Bin in widths array


  // Range check input...
  if (!font || ch < ' ' || ch == 0x7f)
    return (0);
-  else if (font->widths[bin])
+
+  if (font->widths[bin])
    return ((int)(1000.0f * font->widths[bin][ch & 255].width / font->units));
  else if (font->widths[0])		// .notdef
    return ((int)(1000.0f * font->widths[0][0].width / font->units));
@ -881,6 +873,17 @@ ttfGetXHeight(ttf_t *font)		// I - Font
 }


+//
+// 'ttfIsFixedPitch()' - Determine whether a font is fixedpitch.
+//
+
+bool					// O - `true` if fixed pitch, `false` otherwise
+ttfIsFixedPitch(ttf_t *font)		// I - Font
+{
+  return (font ? font->is_fixed : false);
+}
+
+
 //
 // 'copy_name()' - Copy a name string from a font.
 //
@ -1279,7 +1282,7 @@ read_cmap(ttf_t *font)			// I - Font

          // Based on the end code of the segent table, allocate space for the
          // uncompressed cmap table...
-          segCount --;			// Last segment is not used (sigh)
+//          segCount --;			// Last segment is not used (sigh)

 	  font->num_cmap = segments[segCount - 1].endCode + 1;
 	  font->cmap     = cmapptr = (int *)malloc(font->num_cmap * sizeof(int));
@ -1304,17 +1307,18 @@ read_cmap(ttf_t *font)			// I - Font
              {
                // Use an "obscure indexing trick" (words from the spec, not
                // mine) to look up the glyph index...
-                temp = segment->idRangeOffset / 2 + ch - segment->startCode + seg - segCount - 1;
+                temp = segment->idRangeOffset / 2 - segCount + (ch - segment->startCode) + (segment - segments);

-                if (temp < 0 || temp >= numGlyphIdArray || !glyphIdArray[temp])
+                TTF_DEBUG("read_cmap: ch=%d, temp=%d\n", ch, temp);
+                if (temp < 0 || temp >= numGlyphIdArray)
                  glyph = -1;
 		else
-		  glyph = ((glyphIdArray[temp] + segment->idDelta) & 65535) - 1;
+		  glyph = (glyphIdArray[temp] + segment->idDelta) & 65535;
              }
              else
              {
                // Just use idDelta to compute a glyph index...
-                glyph = ((ch + segment->idDelta) & 65535) - 1;
+                glyph = (ch + segment->idDelta) & 65535;
 	      }

 	      cmapptr[ch] = glyph;
@ -1581,6 +1585,8 @@ read_hmtx(ttf_t           *font,	// I - Font
  {
    widths[i].width        = (short)read_ushort(font);
    widths[i].left_bearing = (short)read_short(font);
+
+    TTF_DEBUG("read_hmtx: widths[%d].width=%d, .left_bearing=%d\n", i, widths[i].width, widths[i].left_bearing);
  }

  return (widths);
Author	SHA1	Message	Date
Michael R Sweet	cd80c3037d	Prep for 1.1.4 release.	2023-12-03 16:55:57 -05:00
Michael R Sweet	97934ab995	Add ToUnicode map.	2023-11-19 20:49:30 -05:00
Michael R Sweet	088646e1cf	Drop the FEFF prefix on Unicode strings.	2023-11-19 07:30:17 -05:00
Michael R Sweet	3f0aad7564	Fix another bug in the CMAPv4 code, and a bug in the unit test program.	2023-11-19 07:06:35 -05:00
Michael R Sweet	d36df63b57	Fix a TrueType CMAP decoding bug and add a NotoSans-Regular test page.	2023-11-18 22:15:52 -05:00
Michael R Sweet	a5dfac7495	Bump version.	2023-11-18 18:23:22 -05:00
Michael R Sweet	0258384d53	Range check encrypted string length (Issue #52 )	2023-11-18 18:22:11 -05:00
Michael R Sweet	9fec2195d0	Update changelog.	2023-11-15 10:14:02 -05:00
Michael R Sweet	8ccbdaed94	Update documentation.	2023-11-15 09:28:57 -05:00
Michael R Sweet	4804db38a5	Fix missing ivlen initializer for 40-bit RC4 (Issue #51 )	2023-11-15 08:43:07 -05:00
Michael R Sweet	ddd984215a	Save work (debug printfs, etc.)	2023-11-15 08:38:47 -05:00
Michael R Sweet	efe7c01015	Fix typo and 'make debug'.	2023-11-14 18:38:26 -05:00
Michael R Sweet	600fa4ce59	Fix Unicode font handling (Issue #16 )	2023-11-14 18:19:34 -05:00
Michael R Sweet	688810f143	Save work.	2023-11-13 16:18:02 -05:00
Michael R Sweet	858cc101b6	Save work.	2023-11-13 13:39:06 -05:00