Update documentation and examples makefile.

Clean up the code128 code a bit and use the Helvetica font for the text.

Add support for writing to a PDF file on the command-line vs. just doing
redirection.

.gitignore

@@ -12,14 +12,16 @@
 /configure~
 /doc/pdfio.epub
 /examples/code128
+/examples/image2pdf
 /examples/md2pdf
+/examples/pdf2text
+/examples/pdfioinfo
 /Makefile
 /packages
 /pdfio.pc
 /pdfio.xcodeproj/xcshareddata
 /pdfio-*.tar.gz*
 /pdfio-*.zip*
-/pdfiototext
 /testpdfio
 /testpdfio-*.pdf
 /testttf

CHANGES.md

@@ -14,6 +14,7 @@ v1.4.0 - YYYY-MM-DD
   with `pdfioFileCreateFontObjFromBase` (Issue #84)
 - Fixed reading of PDF files whose trailer is missing a newline (Issue #80)
 - Fixed builds with some versions of VC++ (Issue #81)
+- Fixed validation of date/time values (Issue #83)
 
 
 v1.3.2 - 2024-08-15

Makefile.in

@@ -103,15 +103,33 @@ LIBOBJS		=	\
 			ttf.o
 OBJS		=	\
 			$(LIBOBJS) \
-			pdfiototext.o \
 			testpdfio.o \
 			testttf.o
 TARGETS		=	\
 			$(LIBPDFIO) \
 			$(LIBPDFIO_STATIC) \
-			pdfiototext \
 			testpdfio \
 			testttf
+DOCFILES	=	\
+			doc/pdfio.html \
+			doc/pdfio-512.png \
+			LICENSE \
+			NOTICE
+EXAMPLES	=	\
+			examples/Makefile \
+			examples/Roboto-Bold.ttf \
+			examples/Roboto-Italic.ttf \
+			examples/Roboto-Regular.ttf \
+			examples/RobotoMono-Regular.ttf \
+			examples/code128.c \
+			examples/code128.ttf \
+			examples/image2pdf.c \
+			examples/md2pdf.c \
+			examples/md2pdf.md \
+			examples/mmd.c \
+			examples/mmd.h \
+			examples/pdf2text.c \
+			examples/pdfioinfo.c
 
 
 # Make everything
@@ -152,8 +170,13 @@ install:	$(TARGETS)
 	$(INSTALL) -c -m 644 pdfio.pc $(BUILDROOT)$(libdir)/pkgconfig
 	echo Installing documentation to $(BUILDROOT)$(datadir)/doc/pdfio...
 	$(INSTALL) -d -m 755 $(BUILDROOT)$(datadir)/doc/pdfio
-	for file in doc/pdfio.html doc/pdfio-512.png LICENSE NOTICE; do \
-		$(INSTALL) -c -m 644  $$file $(BUILDROOT)$(datadir)/doc/pdfio; \
+	for file in $(DOCFILES); do \
+		$(INSTALL) -c -m 644 $$file $(BUILDROOT)$(datadir)/doc/pdfio; \
+	done
+	echo Installing examples to $(BUILDROOT)$(datadir)/doc/pdfio/examples...
+	$(INSTALL) -d -m 755 $(BUILDROOT)$(datadir)/doc/pdfio/examples
+	for file in $(EXAMPLES); do \
+		$(INSTALL) -c -m 644 $$file $(BUILDROOT)$(datadir)/doc/pdfio/examples; \
 	done
 	echo Installing man page to $(BUILDROOT)$(mandir)/man3...
 	$(INSTALL) -d -m 755 $(BUILDROOT)$(mandir)/man3
@@ -201,12 +224,6 @@ pdfio1.def: $(LIBOBJS) Makefile
 		grep -v '^_ttf' | sed -e '1,$$s/^_//' | sort >>$@
 
 
-# pdfio text extraction (demo, doesn't handle a lot of things yet)
-pdfiototext:		pdfiototext.o libpdfio.a
-	echo Linking $@...
-	$(CC) $(LDFLAGS) -o $@ pdfiototext.o libpdfio.a $(LIBS)
-
-
 # pdfio test program
 testpdfio:		testpdfio.o libpdfio.a
 	echo Linking $@...

examples/Makefile

@@ -13,14 +13,18 @@
 
 # Common options
 CFLAGS		=	-g $(CPPFLAGS)
-CPPFLAGS	=	-I..
-LIBS		=	-L.. -lpdfio -lz
+#CFLAGS		=	-g -fsanitize=address $(CPPFLAGS)
+CPPFLAGS	=	-I.. -I/usr/local/include
+LIBS		=	-L.. -L/usr/local/lib -lpdfio -lz
 
 
 # Targets
 TARGETS		=	\
 			code128 \
-			md2pdf
+			image2pdf \
+			md2pdf \
+			pdf2text \
+			pdfioinfo
 
 
 # Make everything
@@ -37,10 +41,25 @@ code128:	code128.c
 	$(CC) $(CFLAGS) -o $@ code128.c $(LIBS)
 
 
+# image2pdf
+image2pdf:	image2pdf.c
+	$(CC) $(CFLAGS) -o $@ image2pdf.c $(LIBS)
+
+
 # md2pdf
 md2pdf:		md2pdf.c mmd.c mmd.h
 	$(CC) $(CFLAGS) -o $@ md2pdf.c mmd.c $(LIBS)
 
 
+# pdfio text extraction (demo, doesn't handle a lot of things yet)
+pdf2text:	pdf2text.c
+	$(CC) $(CFLAGS) -o $@ pdf2text.c $(LIBS)
+
+
+# pdfioinfo
+pdfioinfo:	pdfioinfo.c
+	$(CC) $(CFLAGS) -o $@ pdfioinfo.c $(LIBS)
+
+
 # Common dependencies...
 $(TARGETS):	Makefile ../pdfio.h ../pdfio-content.h

examples/code128.c

@@ -23,7 +23,6 @@
 // extended characters are ignored in the source string.
 //
 
-
 static char *				// O - Output string
 make_code128(char       *dst,		// I - Destination buffer
              const char *src,		// I - Source string
@@ -54,9 +53,9 @@ make_code128(char       *dst,		// I - Destination buffer
   static const char code128_start_code_a = '\313';
 					// Start code A
   static const char code128_start_code_b = '\314';
-					// Start code A
+					// Start code B
   static const char code128_start_code_c = '\315';
-					// Start code A
+					// Start code C
   static const char code128_stop = '\316';
 					// Stop pattern
 
@@ -149,7 +148,7 @@ main(int  argc,				// I - Number of command-line arguments
   // Load fonts...
   barcode_font = pdfioFileCreateFontObjFromFile(pdf, "code128.ttf", /*unicode*/false);
   if (text)
-    text_font = pdfioFileCreateFontObjFromFile(pdf, "../testfiles/OpenSans-Regular.ttf", /*unicode*/true);
+    text_font = pdfioFileCreateFontObjFromBase(pdf, "Helvetica");
 
   // Generate Code128 characters for the desired barcode...
   if (!(barcode[0] & 0x80))
@@ -182,7 +181,7 @@ main(int  argc,				// I - Number of command-line arguments
   page_st = pdfioFileCreatePage(pdf, page_dict);
 
   // Draw the page...
-  pdfioContentSetStrokeColorGray(page_st, 0.0);
+  pdfioContentSetFillColorGray(page_st, 0.0);
 
   pdfioContentSetTextFont(page_st, "B128", barcode_height);
   pdfioContentTextBegin(page_st);
@@ -195,7 +194,7 @@ main(int  argc,				// I - Number of command-line arguments
     pdfioContentSetTextFont(page_st, "TEXT", text_height);
     pdfioContentTextBegin(page_st);
     pdfioContentTextMoveTo(page_st, 0.5 * (media_box.x2 - text_width), 9.0);
-    pdfioContentTextShow(page_st, /*unicode*/true, text);
+    pdfioContentTextShow(page_st, /*unicode*/false, text);
     pdfioContentTextEnd(page_st);
   }
 

examples/image2pdf.c

@@ -0,0 +1,139 @@
+//
+// Image example for PDFio.
+//
+// Copyright © 2023-2024 by Michael R Sweet.
+//
+// Licensed under Apache License v2.0.  See the file "LICENSE" for more
+// information.
+//
+// Usage:
+//
+//   ./image2pdf FILENAME.{jpg,png} FILENAME.pdf ["TEXT"]
+//
+
+#include <pdfio.h>
+#include <pdfio-content.h>
+#include <string.h>
+
+
+//
+// 'create_pdf_image_file()' - Create a PDF file of an image with optional caption.
+//
+
+bool					// O - True on success, false on failure
+create_pdf_image_file(
+    const char *pdfname,		// I - PDF filename
+    const char *imagename,		// I - Image filename
+    const char *caption)		// I - Caption filename
+{
+  pdfio_file_t   *pdf;			// PDF file
+  pdfio_obj_t    *font;			// Caption font
+  pdfio_obj_t    *image;		// Image
+  pdfio_dict_t   *dict;			// Page dictionary
+  pdfio_stream_t *page;			// Page stream
+  double         width, height;		// Width and height of image
+  double         swidth, sheight;	// Scaled width and height on page
+  double         tx, ty;		// Position on page
+
+
+  // Create the PDF file...
+  pdf = pdfioFileCreate(pdfname, /*version*/NULL, /*media_box*/NULL,
+                        /*crop_box*/NULL, /*error_cb*/NULL,
+                        /*error_cbdata*/NULL);
+  if (!pdf)
+    return (false);
+
+  // Create a Courier base font for the caption
+  font = pdfioFileCreateFontObjFromBase(pdf, "Courier");
+
+  if (!font)
+  {
+    pdfioFileClose(pdf);
+    return (false);
+  }
+
+  // Create an image object from the JPEG/PNG image file...
+  image = pdfioFileCreateImageObjFromFile(pdf, imagename, true);
+
+  if (!image)
+  {
+    pdfioFileClose(pdf);
+    return (false);
+  }
+
+  // Create a page dictionary with the font and image...
+  dict = pdfioDictCreate(pdf);
+  pdfioPageDictAddFont(dict, "F1", font);
+  pdfioPageDictAddImage(dict, "IM1", image);
+
+  // Create the page and its content stream...
+  page = pdfioFileCreatePage(pdf, dict);
+
+  // Position and scale the image on the page...
+  width  = pdfioImageGetWidth(image);
+  height = pdfioImageGetHeight(image);
+
+  // Default media_box is "universal" 595.28x792 points (8.27x11in or
+  // 210x279mm).  Use margins of 36 points (0.5in or 12.7mm) with another
+  // 36 points for the caption underneath...
+  swidth  = 595.28 - 72.0;
+  sheight = swidth * height / width;
+  if (sheight > (792.0 - 36.0 - 72.0))
+  {
+    sheight = 792.0 - 36.0 - 72.0;
+    swidth  = sheight * width / height;
+  }
+
+  tx = 0.5 * (595.28 - swidth);
+  ty = 0.5 * (792 - 36 - sheight);
+
+  pdfioContentDrawImage(page, "IM1", tx, ty + 36.0, swidth, sheight);
+
+  // Draw the caption in black...
+  pdfioContentSetFillColorDeviceGray(page, 0.0);
+
+  // Compute the starting point for the text - Courier is monospaced
+  // with a nominal width of 0.6 times the text height...
+  tx = 0.5 * (595.28 - 18.0 * 0.6 * strlen(caption));
+
+  // Position and draw the caption underneath...
+  pdfioContentTextBegin(page);
+  pdfioContentSetTextFont(page, "F1", 18.0);
+  pdfioContentTextMoveTo(page, tx, ty);
+  pdfioContentTextShow(page, /*unicode*/false, caption);
+  pdfioContentTextEnd(page);
+
+  // Close the page stream and the PDF file...
+  pdfioStreamClose(page);
+  pdfioFileClose(pdf);
+
+  return (true);
+}
+
+
+//
+// 'main()' - Produce a single-page file from an image.
+//
+
+int					// O - Exit status
+main(int  argc,				// I - Number of command-line arguments
+     char *argv[])			// I - Command-line arguments
+{
+  const char	*imagefile,		// Image filename
+		*pdffile,		// PDF filename
+		*caption;		// Caption text
+
+
+  // Get the image file, PDF file, and optional caption text from the command-line...
+  if (argc < 3 || argc > 4)
+  {
+    fputs("Usage: image2pdf FILENAME.{jpg,png} FILENAME.pdf [\"TEXT\"]\n", stderr);
+    return (1);
+  }
+
+  imagefile = argv[1];
+  pdffile   = argv[2];
+  caption   = argv[3];
+
+  return (create_pdf_image_file(imagefile, pdffile, caption) ? 0 : 1);
+}

examples/md2pdf.c

@@ -8,6 +8,7 @@
 //
 // Usage:
 //
+//   ./md2pdf FILENAME.md FILENAME.pdf
 //   ./md2pdf FILENAME.md >FILENAME.pdf
 //
 // The generated PDF file is formatted for a "universal" paper size (8.27x11",
@@ -40,7 +41,7 @@ typedef enum doccolor_e			// Document color enumeration
 {
   DOCCOLOR_BLACK,			// #000
   DOCCOLOR_RED,				// #900
-  DOCCOLOR_GREEN,			// #090
+  DOCCOLOR_ORANGE,			// #CC0
   DOCCOLOR_BLUE,			// #00C
   DOCCOLOR_LTGRAY,			// #EEE
   DOCCOLOR_GRAY				// #555
@@ -88,17 +89,37 @@ typedef struct doctarget_s		// Document target info
 
 #define DOCTARGET_MAX	1000		// Maximum number of targets per document
 
+typedef struct doctoc_s			// Document table-of-contents entry
+{
+  int		level;			// Level
+  int		count;			// Total number of child entries
+  pdfio_obj_t	*obj;			// Dictionary object
+  pdfio_dict_t	*dict;			// Dictionary value
+} doctoc_t;
+
+#define DOCTOC_MAX	1000		// Maximum number of TOC entries
+
 typedef struct docdata_s		// Document formatting data
 {
+  // State for the whole document
   pdfio_file_t	*pdf;			// PDF file
   pdfio_rect_t	media_box;		// Media (page) box
   pdfio_rect_t	crop_box;		// Crop box (for margins)
   pdfio_rect_t	art_box;		// Art box (for markdown content)
   pdfio_obj_t	*fonts[DOCFONT_MAX];	// Embedded fonts
+  double	font_space;		// Unit width of a space
   size_t	num_images;		// Number of embedded images
   docimage_t	images[DOCIMAGE_MAX];	// Embedded images
   const char	*title;			// Document title
   char		*heading;		// Current document heading
+  size_t	num_actions;		// Number of actions for this document
+  docaction_t	actions[DOCACTION_MAX];	// Actions for this document
+  size_t	num_targets;		// Number of targets for this document
+  doctarget_t	targets[DOCTARGET_MAX];	// Targets for this document
+  size_t	num_toc;		// Number of table-of-contents entries
+  doctoc_t	toc[DOCTOC_MAX];	// Table-of-contents entries
+
+  // State for the current page
   pdfio_stream_t *st;			// Current page stream
   double	y;			// Current position on page
   docfont_t	font;			// Current font
@@ -108,10 +129,6 @@ typedef struct docdata_s		// Document formatting data
   pdfio_obj_t	*annots_obj;		// Annotations object (for links)
   size_t	num_links;		// Number of links for this page
   doclink_t	links[DOCLINK_MAX];	// Links for this page
-  size_t	num_actions;		// Number of actions for this document
-  docaction_t	actions[DOCACTION_MAX];	// Actions for this document
-  size_t	num_targets;		// Number of targets for this document
-  doctarget_t	targets[DOCTARGET_MAX];	// Targets for this document
 } docdata_t;
 
 typedef struct linefrag_s		// Line fragment
@@ -192,10 +209,17 @@ static const char * const docfont_names[] =
   "FM"
 };
 
+#define BQ_PADDING	18.0		// Padding for block quotes
+#define BQ_THICKNESS	3.0		// Thickness of block quote bar
+
+#define CODE_PADDING	4.5		// Padding for code blocks
+
 #define IMAGE_PPI	100.0		// Pixels per inch for images
 
 #define LINE_HEIGHT	1.4		// Multiplier for line height
 
+#define LIST_PADDING	36.0		// Padding/indentation for lists
+
 #define SIZE_BODY	11.0		// Size of body text (points)
 #define SIZE_CODEBLOCK	10.0		// Size of code block text (points)
 #define SIZE_HEADFOOT	9.0		// Size of header/footer text (points)
@@ -231,18 +255,19 @@ static void	add_links(docdata_t *dd);
 static pdfio_obj_t *find_image(docdata_t  *dd, const char *url, size_t *imagenum);
 static void	format_block(docdata_t *dd, mmd_t *block, docfont_t deffont, double fsize, double left, double right, const char *leader);
 static void	format_code(docdata_t *dd, mmd_t *block, double left, double right);
-static void	format_doc(docdata_t *dd, mmd_t *doc, double left, double right);
+static void	format_doc(docdata_t *dd, mmd_t *doc, docfont_t deffont, double left, double right);
 static void	format_table(docdata_t *dd, mmd_t *table, double left, double right);
 static void	make_target_name(char *dst, const char *src, size_t dstsize);
 static double	measure_cell(docdata_t *dd, mmd_t *cell, tablecol_t *col);
 static mmd_t	*mmd_walk_next(mmd_t *top, mmd_t *node);
 static void	new_page(docdata_t *dd);
 static ssize_t	output_cb(void *output_cbdata, const void *buffer, size_t bytes);
-static void	render_line(docdata_t *dd, double margin_left, double margin_top, double lineheight, size_t num_frags, linefrag_t *frags);
+static void	render_line(docdata_t *dd, double margin_left, double need_bottom, double lineheight, size_t num_frags, linefrag_t *frags);
 static void	render_row(docdata_t *dd, size_t num_cols, tablecol_t *cols, tablerow_t *row);
 static void	set_color(docdata_t *dd, doccolor_t color);
 static void	set_font(docdata_t *dd, docfont_t font, double fsize);
 static void	write_actions(docdata_t *dd);
+static void	write_toc(docdata_t *dd);
 
 
 //
@@ -262,9 +287,10 @@ main(int  argc,				// I - Number of command-line arguments
   setbuf(stderr, NULL);
 
   // Get the markdown file from the command-line...
-  if (argc != 2)
+  if (argc < 2 || argc > 3)
   {
-    fputs("Usage: md2pdf FILENANE.md >FILENAME.pdf\n", stderr);
+    fputs("Usage: md2pdf FILENANE.md [FILENAME.pdf]\n", stderr);
+    fputs("       md2pdf FILENANE.md >FILENAME.pdf\n", stderr);
     return (1);
   }
 
@@ -287,15 +313,23 @@ main(int  argc,				// I - Number of command-line arguments
   dd.art_box.x2  = PAGE_RIGHT;
   dd.art_box.y2  = PAGE_TOP;
 
-  dd.title       = mmdGetMetadata(doc, "title");
+  if ((dd.title = mmdGetMetadata(doc, "title")) == NULL)
+    dd.art_box.y2 = PAGE_HEADER;	// No header if there is no title
 
-  // Output a PDF file to the standard output...
+  if (argc == 2)
+  {
+    // Output a PDF file to the standard output...
 #ifdef _WIN32
-  setmode(1, O_BINARY);			// Force binary output on Windows
+    setmode(1, O_BINARY);		// Force binary output on Windows
 #endif // _WIN32
 
-  if ((dd.pdf = pdfioFileCreateOutput(output_cb, /*output_cbdata*/NULL, /*version*/NULL, /*media_box*/NULL, /*crop_box*/NULL, /*error_cb*/NULL, /*error_data*/NULL)) == NULL)
+    if ((dd.pdf = pdfioFileCreateOutput(output_cb, /*output_cbdata*/NULL, /*version*/NULL, /*media_box*/NULL, /*crop_box*/NULL, /*error_cb*/NULL, /*error_data*/NULL)) == NULL)
+      return (1);
+  }
+  else if ((dd.pdf = pdfioFileCreate(argv[2], /*version*/NULL, /*media_box*/NULL, /*crop_box*/NULL, /*error_cb*/NULL, /*error_data*/NULL)) == NULL)
+  {
     return (1);
+  }
 
   if ((value = mmdGetMetadata(doc, "author")) != NULL)
     pdfioFileSetAuthor(dd.pdf, value);
@@ -323,11 +357,13 @@ main(int  argc,				// I - Number of command-line arguments
 #endif // USE_TRUETYPE
   }
 
+  dd.font_space = pdfioContentTextMeasure(dd.fonts[DOCFONT_REGULAR], " ", 1.0);
+
   // Add images...
   add_images(&dd, doc);
 
   // Parse the markdown document...
-  format_doc(&dd, doc, dd.art_box.x1, dd.art_box.x2);
+  format_doc(&dd, doc, DOCFONT_REGULAR, dd.art_box.x1, dd.art_box.x2);
 
   // Close the PDF and return...
   if (dd.st)
@@ -335,7 +371,12 @@ main(int  argc,				// I - Number of command-line arguments
     pdfioStreamClose(dd.st);
     add_links(&dd);
   }
+
   write_actions(&dd);
+
+  if (dd.num_toc > 0)
+    write_toc(&dd);
+
   pdfioFileClose(dd.pdf);
 
   mmdFree(doc);
@@ -539,27 +580,31 @@ format_block(docdata_t  *dd,		// I - Document data
 		width,			// Width of current fragment
 		wswidth,		// Width of whitespace
 		margin_left,		// Left margin
-		margin_top,		// Top margin
+		need_bottom,		// Space needed after this block
 		height,			// Height of current fragment
 		lineheight;		// Height of current line
 
 
   blocktype  = mmdGetType(block);
 
-  if ((blocktype >= MMD_TYPE_TABLE_HEADER_CELL && blocktype <= MMD_TYPE_TABLE_BODY_CELL_RIGHT) || blocktype == MMD_TYPE_LIST_ITEM)
-    margin_top = 0.0;
+  if (mmdGetNextSibling(block))
+    need_bottom = 3.0 * SIZE_BODY * LINE_HEIGHT;
   else
-    margin_top = fsize * LINE_HEIGHT;
+    need_bottom = 0.0;
 
   if (leader)
   {
     // Add leader text on first line...
-    frags[0].width  = pdfioContentTextMeasure(dd->fonts[deffont], leader, fsize);
-    frags[0].height = fsize;
-    frags[0].x      = left - frags[0].width;
-    frags[0].text   = leader;
-    frags[0].font   = deffont;
-    frags[0].color  = DOCCOLOR_BLACK;
+    frags[0].type     = MMD_TYPE_NORMAL_TEXT;
+    frags[0].width    = pdfioContentTextMeasure(dd->fonts[deffont], leader, fsize);
+    frags[0].height   = fsize;
+    frags[0].x        = left - frags[0].width;
+    frags[0].imagenum = 0;
+    frags[0].text     = leader;
+    frags[0].url      = NULL;
+    frags[0].ws       = false;
+    frags[0].font     = deffont;
+    frags[0].color    = DOCCOLOR_BLACK;
 
     num_frags  = 1;
     lineheight = fsize * LINE_HEIGHT;
@@ -583,7 +628,7 @@ format_block(docdata_t  *dd,		// I - Document data
     imagenum = 0;
     url      = mmdGetURL(current);
     ws       = mmdGetWhitespace(current);
-    wswidth  = 0.0;
+    wswidth  = ws ? dd->font_space * fsize : 0.0;
     next     = mmd_walk_next(block, current);
 
     // Process the node...
@@ -620,13 +665,21 @@ format_block(docdata_t  *dd,		// I - Document data
       else
         margin_left = 0.0;
 
-      render_line(dd, margin_left, margin_top, lineheight, num_frags, frags);
+      render_line(dd, margin_left, need_bottom, lineheight, num_frags, frags);
 
-      num_frags  = 0;
-      frag       = frags;
-      x          = left;
-      lineheight = 0.0;
-      margin_top = 0.0;
+      if (deffont == DOCFONT_ITALIC)
+      {
+        // Add an orange bar to the left of block quotes...
+        set_color(dd, DOCCOLOR_ORANGE);
+        pdfioContentPathRect(dd->st, left - BQ_PADDING, dd->y - (LINE_HEIGHT - 1.0) * fsize - BQ_THICKNESS, BQ_THICKNESS, lineheight + 2.0 * BQ_THICKNESS);
+        pdfioContentFill(dd->st, /*even_odd*/false);
+      }
+
+      num_frags   = 0;
+      frag        = frags;
+      x           = left;
+      lineheight  = 0.0;
+      need_bottom = 0.0;
 
       continue;
     }
@@ -660,9 +713,6 @@ format_block(docdata_t  *dd,		// I - Document data
 
       width  = pdfioContentTextMeasure(dd->fonts[font], text, fsize);
       height = fsize * LINE_HEIGHT;
-
-      if (ws)
-	wswidth = pdfioContentTextMeasure(dd->fonts[font], " ", fsize);
     }
 
     // See if this node will fit on the current line...
@@ -676,18 +726,31 @@ format_block(docdata_t  *dd,		// I - Document data
       else
         margin_left = 0.0;
 
-      render_line(dd, margin_left, margin_top, lineheight, num_frags, frags);
+      render_line(dd, margin_left, need_bottom, lineheight, num_frags, frags);
 
-      num_frags  = 0;
-      frag       = frags;
-      x          = left;
-      lineheight = 0.0;
-      margin_top = 0.0;
+      num_frags   = 0;
+      frag        = frags;
+      x           = left;
+      lineheight  = 0.0;
+      need_bottom = 0.0;
+
+      if (deffont == DOCFONT_ITALIC)
+      {
+        // Add an orange bar to the left of block quotes...
+        set_color(dd, DOCCOLOR_ORANGE);
+        pdfioContentSave(dd->st);
+        pdfioContentSetLineWidth(dd->st, 3.0);
+        pdfioContentPathMoveTo(dd->st, left - 6.0, dd->y - (LINE_HEIGHT - 1.0) * fsize);
+        pdfioContentPathLineTo(dd->st, left - 6.0, dd->y + fsize);
+        pdfioContentStroke(dd->st);
+        pdfioContentRestore(dd->st);
+      }
     }
 
     // Add the current node to the fragment list
     if (num_frags == 0)
     {
+      // No leading whitespace at the start of the line
       ws      = false;
       wswidth = 0.0;
     }
@@ -719,7 +782,19 @@ format_block(docdata_t  *dd,		// I - Document data
     else
       margin_left = 0.0;
 
-    render_line(dd, margin_left, margin_top, lineheight, num_frags, frags);
+    render_line(dd, margin_left, need_bottom, lineheight, num_frags, frags);
+
+    if (deffont == DOCFONT_ITALIC)
+    {
+      // Add an orange bar to the left of block quotes...
+      set_color(dd, DOCCOLOR_ORANGE);
+      pdfioContentSave(dd->st);
+      pdfioContentSetLineWidth(dd->st, 3.0);
+      pdfioContentPathMoveTo(dd->st, left - 6.0, dd->y - (LINE_HEIGHT - 1.0) * fsize);
+      pdfioContentPathLineTo(dd->st, left - 6.0, dd->y + fsize);
+      pdfioContentStroke(dd->st);
+      pdfioContentRestore(dd->st);
+    }
   }
 }
 
@@ -738,19 +813,27 @@ format_code(docdata_t *dd,		// I - Document data
   double	lineheight;		// Line height
 
 
+  // Compute line height...
+  lineheight = SIZE_CODEBLOCK * LINE_HEIGHT;
+
   // Start a new page as needed...
   if (!dd->st)
     new_page(dd);
 
-  lineheight = SIZE_CODEBLOCK * LINE_HEIGHT;
-  dd->y      -= 2.0 * lineheight;
-  if (dd->y < dd->art_box.y1)
+  dd->y -= lineheight + CODE_PADDING;
+
+  if ((dd->y - lineheight) < dd->art_box.y1)
   {
     new_page(dd);
 
-    dd->y -= lineheight;
+    dd->y -= lineheight + CODE_PADDING;
   }
 
+  // Draw the top padding...
+  set_color(dd, DOCCOLOR_LTGRAY);
+  pdfioContentPathRect(dd->st, left - CODE_PADDING, dd->y + SIZE_CODEBLOCK, right - left + 2.0 * CODE_PADDING, CODE_PADDING);
+  pdfioContentFillAndStroke(dd->st, false);
+
   // Start a code text block...
   set_font(dd, DOCFONT_MONOSPACE, SIZE_CODEBLOCK);
   pdfioContentTextBegin(dd->st);
@@ -759,7 +842,7 @@ format_code(docdata_t *dd,		// I - Document data
   for (code = mmdGetFirstChild(block); code; code = mmdGetNextSibling(code))
   {
     set_color(dd, DOCCOLOR_LTGRAY);
-    pdfioContentPathRect(dd->st, left - 3.0, dd->y - (LINE_HEIGHT - 1.0) * SIZE_CODEBLOCK, right - left + 3.0, lineheight);
+    pdfioContentPathRect(dd->st, left - CODE_PADDING, dd->y - (LINE_HEIGHT - 1.0) * SIZE_CODEBLOCK, right - left + 2.0 * CODE_PADDING, lineheight);
     pdfioContentFillAndStroke(dd->st, false);
 
     set_color(dd, DOCCOLOR_RED);
@@ -784,6 +867,12 @@ format_code(docdata_t *dd,		// I - Document data
 
   // End the current text block...
   pdfioContentTextEnd(dd->st);
+  dd->y += lineheight;
+
+  // Draw the bottom padding...
+  set_color(dd, DOCCOLOR_LTGRAY);
+  pdfioContentPathRect(dd->st, left - CODE_PADDING, dd->y - CODE_PADDING - (LINE_HEIGHT - 1.0) * SIZE_CODEBLOCK, right - left + 2.0 * CODE_PADDING, CODE_PADDING);
+  pdfioContentFillAndStroke(dd->st, false);
 }
 
 
@@ -794,6 +883,7 @@ format_code(docdata_t *dd,		// I - Document data
 static void
 format_doc(docdata_t *dd,		// I - Document data
            mmd_t     *doc,		// I - Document node to format
+           docfont_t deffont,		// I - Default font
            double    left,		// I - Left margin
            double    right)		// I - Right margin
 {
@@ -822,27 +912,31 @@ format_doc(docdata_t *dd,		// I - Document data
       default :
           break;
 
+      case MMD_TYPE_THEMATIC_BREAK :
+          // Force a page break
+          dd->y = dd->art_box.y1;
+          break;
+
       case MMD_TYPE_BLOCK_QUOTE :
-          format_doc(dd, current, left + 36.0, right - 36.0);
+          format_doc(dd, current, DOCFONT_ITALIC, left + BQ_PADDING, right - BQ_PADDING);
           break;
 
       case MMD_TYPE_ORDERED_LIST :
       case MMD_TYPE_UNORDERED_LIST :
-          if (dd->st)
-            dd->y -= SIZE_BODY * LINE_HEIGHT;
+	  dd->y -= SIZE_BODY * LINE_HEIGHT;
 
-          format_doc(dd, current, left + 36.0, right);
+          format_doc(dd, current, deffont, left + LIST_PADDING, right);
           break;
 
       case MMD_TYPE_LIST_ITEM :
           if (doctype == MMD_TYPE_ORDERED_LIST)
           {
             snprintf(leader, sizeof(leader), "%d. ", i);
-            format_block(dd, current, DOCFONT_REGULAR, SIZE_BODY, left, right, leader);
+            format_block(dd, current, deffont, SIZE_BODY, left, right, leader);
           }
           else
           {
-            format_block(dd, current, DOCFONT_REGULAR, SIZE_BODY, left, right, /*leader*/"• ");
+            format_block(dd, current, deffont, SIZE_BODY, left, right, /*leader*/"• ");
           }
           break;
 
@@ -852,13 +946,41 @@ format_doc(docdata_t *dd,		// I - Document data
       case MMD_TYPE_HEADING_4 :
       case MMD_TYPE_HEADING_5 :
       case MMD_TYPE_HEADING_6 :
-          if (dd->heading)
-            free(dd->heading);
-
+          // Update the current heading
+          free(dd->heading);
           dd->heading = mmdCopyAllText(current);
 
+          // Add a blank line before the heading...
+	  dd->y -= heading_sizes[curtype - MMD_TYPE_HEADING_1] * LINE_HEIGHT;
+
+	  // Format the heading...
           format_block(dd, current, DOCFONT_BOLD, heading_sizes[curtype - MMD_TYPE_HEADING_1], left, right, /*leader*/NULL);
 
+          // Add the heading to the table-of-contents...
+          if (dd->num_toc < DOCTOC_MAX)
+          {
+            doctoc_t *t = dd->toc + dd->num_toc;
+					// New TOC
+	    pdfio_array_t *dest;	// Destination array
+
+            t->level = curtype - MMD_TYPE_HEADING_1;
+            t->dict  = pdfioDictCreate(dd->pdf);
+            t->obj   = pdfioFileCreateObj(dd->pdf, t->dict);
+            dest     = pdfioArrayCreate(dd->pdf);
+
+	    pdfioArrayAppendObj(dest, pdfioFileGetPage(dd->pdf, pdfioFileGetNumPages(dd->pdf) - 1));
+	    pdfioArrayAppendName(dest, "XYZ");
+	    pdfioArrayAppendNumber(dest, PAGE_LEFT);
+	    pdfioArrayAppendNumber(dest, dd->y + heading_sizes[curtype - MMD_TYPE_HEADING_1] * LINE_HEIGHT);
+	    pdfioArrayAppendNumber(dest, 0.0);
+
+	    pdfioDictSetArray(t->dict, "Dest", dest);
+	    pdfioDictSetString(t->dict, "Title", pdfioStringCreate(dd->pdf, dd->heading));
+
+            dd->num_toc ++;
+          }
+
+	  // Add the heading to the list of link targets...
           if (dd->num_targets < DOCTARGET_MAX)
           {
             doctarget_t *t = dd->targets + dd->num_targets;
@@ -873,15 +995,27 @@ format_doc(docdata_t *dd,		// I - Document data
           break;
 
       case MMD_TYPE_PARAGRAPH :
-          format_block(dd, current, DOCFONT_REGULAR, SIZE_BODY, left, right, /*leader*/NULL);
+          // Add a blank line before the paragraph...
+	  dd->y -= SIZE_BODY * LINE_HEIGHT;
+
+	  // Format the paragraph...
+          format_block(dd, current, deffont, SIZE_BODY, left, right, /*leader*/NULL);
           break;
 
       case MMD_TYPE_TABLE :
+          // Add a blank line before the paragraph...
+	  dd->y -= SIZE_BODY * LINE_HEIGHT;
+
+	  // Format the table...
           format_table(dd, current, left, right);
           break;
 
       case MMD_TYPE_CODE_BLOCK :
-          format_code(dd, current, left + 36.0, right - 36.0);
+          // Add a blank line before the code block...
+	  dd->y -= SIZE_BODY * LINE_HEIGHT;
+
+	  // Format the code block...
+          format_code(dd, current, left + CODE_PADDING, right - CODE_PADDING);
           break;
     }
   }
@@ -915,14 +1049,10 @@ format_table(docdata_t *dd,		// I - Document data
 
 
   // Find all of the rows and columns in the table...
-  num_cols = num_rows = 0;
-
   memset(cols, 0, sizeof(cols));
   memset(rows, 0, sizeof(rows));
 
-  rowptr = rows;
-
-  for (current = mmdGetFirstChild(table); current && num_rows < TABLEROW_MAX; current = next)
+  for (num_cols = 0, num_rows = 0, rowptr = rows, current = mmdGetFirstChild(table); current && num_rows < TABLEROW_MAX; current = next)
   {
     next = mmd_walk_next(table, current);
     type = mmdGetType(current);
@@ -1014,9 +1144,6 @@ format_table(docdata_t *dd,		// I - Document data
   }
 
   // Render each table row...
-  if (dd->st)
-    dd->y -= SIZE_TABLE * LINE_HEIGHT;
-
   for (row = 0, rowptr = rows; row < num_rows; row ++, rowptr ++)
     render_row(dd, num_cols, cols, rowptr);
 }
@@ -1238,15 +1365,15 @@ new_page(docdata_t *dd)			// I - Document data
 
   // Prep the new page...
   page_dict = pdfioDictCreate(dd->pdf);
+
   dd->annots_array = pdfioArrayCreate(dd->pdf);
   dd->annots_obj   = pdfioFileCreateArrayObj(dd->pdf, dd->annots_array);
+  pdfioDictSetObj(page_dict, "Annots", dd->annots_obj);
 
   pdfioDictSetRect(page_dict, "MediaBox", &dd->media_box);
 //  pdfioDictSetRect(page_dict, "CropBox", &dd->crop_box);
   pdfioDictSetRect(page_dict, "ArtBox", &dd->art_box);
 
-  pdfioDictSetObj(page_dict, "Annots", dd->annots_obj);
-
   for (fontface = DOCFONT_REGULAR; fontface < DOCFONT_MAX; fontface ++)
     pdfioPageDictAddFont(page_dict, docfont_names[fontface], dd->fonts[fontface]);
 
@@ -1343,7 +1470,7 @@ output_cb(void       *output_cbdata,	// I - Callback data (not used)
 static void
 render_line(docdata_t  *dd,		// I - Document data
             double     margin_left,	// I - Left margin
-            double     margin_top,	// I - Top margin
+            double     need_bottom,	// I - How much space is needed after
             double     lineheight,	// I - Height of line
             size_t     num_frags,	// I - Number of line fragments
             linefrag_t *frags)		// I - Line fragments
@@ -1354,13 +1481,10 @@ render_line(docdata_t  *dd,		// I - Document data
 
 
   if (!dd->st)
-  {
     new_page(dd);
-    margin_top = 0.0;
-  }
 
-  dd->y -= margin_top + lineheight;
-  if (dd->y < dd->art_box.y1)
+  dd->y -= lineheight;
+  if ((dd->y - need_bottom) < dd->art_box.y1)
   {
     new_page(dd);
 
@@ -1398,9 +1522,6 @@ render_line(docdata_t  *dd,		// I - Document data
     else if (frag->text)
     {
       // Draw text
-      set_color(dd, frag->color);
-      set_font(dd, frag->font, frag->height);
-
       if (!in_text)
       {
 	pdfioContentTextBegin(dd->st);
@@ -1409,12 +1530,21 @@ render_line(docdata_t  *dd,		// I - Document data
 	in_text = true;
       }
 
-      if (frag->ws)
-	pdfioContentTextShowf(dd->st, UNICODE_VALUE, " %s", frag->text);
-      else
-	pdfioContentTextShow(dd->st, UNICODE_VALUE, frag->text);
+      if (frag->ws && frag->font == DOCFONT_MONOSPACE)
+      {
+	set_font(dd, DOCFONT_REGULAR, frag->height);
+	pdfioContentTextShow(dd->st, UNICODE_VALUE, " ");
+      }
 
-      if (frag->type == MMD_TYPE_LINKED_TEXT && frag->url && dd->num_links < DOCLINK_MAX)
+      set_color(dd, frag->color);
+      set_font(dd, frag->font, frag->height);
+
+      if (frag->font == DOCFONT_MONOSPACE)
+	pdfioContentTextShow(dd->st, UNICODE_VALUE, frag->text);
+      else
+	pdfioContentTextShowf(dd->st, UNICODE_VALUE, "%s%s", frag->ws ? " " : "", frag->text);
+
+      if (frag->url && dd->num_links < DOCLINK_MAX)
       {
         doclink_t *l = dd->links + dd->num_links;
 					// Pointer to this link record
@@ -1545,9 +1675,9 @@ set_color(docdata_t  *dd,		// I - Document data
         pdfioContentSetFillColorDeviceRGB(dd->st, 0.6, 0.0, 0.0);
         pdfioContentSetStrokeColorDeviceRGB(dd->st, 0.6, 0.0, 0.0);
         break;
-    case DOCCOLOR_GREEN :
-        pdfioContentSetFillColorDeviceRGB(dd->st, 0.0, 0.6, 0.0);
-        pdfioContentSetStrokeColorDeviceRGB(dd->st, 0.0, 0.6, 0.0);
+    case DOCCOLOR_ORANGE :
+        pdfioContentSetFillColorDeviceRGB(dd->st, 1.0, 0.5, 0.0);
+        pdfioContentSetStrokeColorDeviceRGB(dd->st, 1.0, 0.5, 0.0);
         break;
     case DOCCOLOR_BLUE :
         pdfioContentSetFillColorDeviceRGB(dd->st, 0.0, 0.0, 0.8);
@@ -1629,3 +1759,107 @@ write_actions(docdata_t *dd)		// I - Document data
     pdfioObjClose(a->obj);
   }
 }
+
+
+//
+// 'write_toc()' - Write the table-of-contents outline.
+//
+
+static void
+write_toc(docdata_t *dd)		// I - Document data
+{
+  size_t	i, j;			// Looping vars
+  doctoc_t	*t,			// Table-of-contents entry
+		*nt,			// Next entry
+		*levels[6];		// Current entries for each level
+  int		level;			// Current level
+  pdfio_dict_t	*dict;			// Outline dictionary
+  pdfio_obj_t	*obj;			// Outline object
+
+
+  // Initialize the various TOC levels...
+  levels[0] = levels[1] = levels[2] = levels[3] = levels[4] = levels[5] = NULL;
+
+  // Scan the table of contents and finalize the dictionaries...
+  for (i = 0, t = dd->toc; i < dd->num_toc; i ++, t ++)
+  {
+    // Set parent, previous, and next entries...
+    if (t->level > 0 && levels[t->level - 1])
+      pdfioDictSetObj(t->dict, "Parent", levels[t->level - 1]->obj);
+
+    if (levels[t->level])
+      pdfioDictSetObj(t->dict, "Prev", levels[t->level]->obj);
+
+    for (j = i + 1, nt = t + 1; j < dd->num_toc; j ++, nt ++)
+    {
+      if (nt->level == t->level)
+      {
+	pdfioDictSetObj(t->dict, "Next", nt->obj);
+        break;
+      }
+      else if (nt->level < t->level)
+      {
+        break;
+      }
+    }
+
+    // First, last, and count...
+    for (level = 0; level < t->level; level ++)
+      levels[level]->count ++;
+
+    levels[t->level] = t;
+
+    if ((i + 1) < dd->num_toc && t[1].level > t->level)
+      pdfioDictSetObj(t->dict, "First", t[1].obj);
+
+    if ((i + 1) >= dd->num_toc)
+    {
+      // Close out all levels...
+      for (level = t->level; level > 0; level --)
+      {
+        pdfioDictSetObj(levels[level - 1]->dict, "Last", levels[level]->obj);
+	levels[level] = NULL;
+      }
+    }
+    else if (t->level > t[1].level)
+    {
+      // Close out N levels...
+      for (level = t->level; level > t[1].level; level --)
+      {
+        pdfioDictSetObj(levels[level - 1]->dict, "Last", levels[level]->obj);
+	levels[level] = NULL;
+      }
+    }
+  }
+
+  // Create the top-level outline object...
+  dict = pdfioDictCreate(dd->pdf);
+  obj  = pdfioFileCreateObj(dd->pdf, dict);
+
+  pdfioDictSetName(dict, "Type", "Outline");
+  pdfioDictSetNumber(dict, "Count", dd->num_toc);
+  pdfioDictSetObj(dict, "First", dd->toc[0].obj);
+
+  // Close the objects for the entries...
+  for (i = 0, t = dd->toc; i < dd->num_toc; i ++, t ++)
+  {
+    if (t->level == 0)
+      pdfioDictSetObj(dict, "Last", t->obj);
+
+    if (t->count)
+    {
+      // Set Count value...
+      if (t->level == 0)
+        pdfioDictSetNumber(t->dict, "Count", t->count);
+      else
+        pdfioDictSetNumber(t->dict, "Count", -t->count);
+    }
+
+    pdfioObjClose(t->obj);
+  }
+
+  // Close the outline object and add it to the document catalog...
+  pdfioObjClose(obj);
+
+  pdfioDictSetObj(pdfioFileGetCatalog(dd->pdf), "Outlines", obj);
+}

examples/md2pdf.md

@@ -1,22 +1,10 @@
 ---
-title: Markdown to PDF Converter Example
+title: Markdown to PDF Converter Test File
 ...
 
-Markdown to PDF Converter Example
-=================================
 
-The `md2pdf` example program reads a markdown file and formats the content onto
-pages in a PDF file.  It demonstrates how to:
-
-- Embed base and TrueType fonts,
-- Format text,
-- Embed JPEG and PNG images,
-- Add headers and footers, and
-- Add hyperlinks.
-
-
-Source Files
-------------
+Markdown to PDF Converter Test File
+===================================
 
 The `md2pdf` program is organized into three source files: `md2pdf.c` which
 contains the code to format the markdown content and `mmd.h` and `mmd.c` (from
@@ -24,4 +12,73 @@ the [Miniature Markdown Library][MMD] project) which load the markdown content.
 
 [MMD]: https://www.msweet.org/mmd/
 
+This is a test file for `md2pdf`.  Here is a bullet list:
 
+- Embed base and TrueType fonts,
+- Format text with embedded JPEG and PNG images and check boxes, with support
+  for wrapping, alignment in table cells, leader text (as used for lists), and
+  variable line height,
+- Add headers and footers, and
+- Add hyperlinks and document platform.
+
+And here is an ordered list:
+
+1. Embed base and TrueType fonts,
+2. Format text with embedded JPEG and PNG images and check boxes, with support
+   for wrapping, alignment in table cells, leader text (as used for lists), and
+   variable line height,
+3. Add headers and footers, and
+4. Add hyperlinks and document platform.
+
+
+Code Blocks
+-----------
+
+```
+0        1         2         3         4         5         6         7         8
+12345678901234567890123456789012345678901234567890123456789012345678901234567890
+```
+
+
+Images
+------
+
+PDFio book cover image:
+
+![PDFio](../doc/pdfio-epub.png)
+
+
+Tables
+------
+
+Table with leading/trailing pipes:
+
+| Heading 1 | Heading 2 | Heading 3 |
+| --------- | --------- | --------- |
+| Cell 1,1  | Cell 1,2  | Cell 1,3  |
+| Cell 2,1  | Cell 2,2  | Cell 2,3  |
+| Cell 3,1  | Cell 3,2  | Cell 3,3  |
+
+Table without leading/trailing pipes:
+
+Heading 1 | Heading 2 | Heading 3
+--------- | --------- | ---------
+Cell 1,1  | Cell 1,2  | Cell 1,3
+Cell 2,1  | Cell 2,2  | Cell 2,3
+Cell 3,1  | Cell 3,2  | Cell 3,3
+
+Table with alignment:
+
+Left Alignment | Center Alignment | Right Alignment
+:-------- | :-------: | --------:
+Cell 1,1  | Cell 1,2  |        1
+Cell 2,1  | Cell 2,2  |       12
+Cell 3,1  | Cell 3,2  |      123
+
+Table in block quote:
+
+> Heading 1 | Heading 2 | Heading 3
+> --------- | --------- | ---------
+> Cell 1,1  | Cell 1,2  | Cell 1,3
+> Cell 2,1  | Cell 2,2  | Cell 2,3
+> Cell 3,1  | Cell 3,2  | Cell 3,3

examples/mmd.c

@@ -166,7 +166,7 @@ mmdCopyAllText(mmd_t *node)		// I - Parent node
   char		*all = NULL,		// String buffer
 		*allptr = NULL,		// Pointer into string buffer
 		*temp;			// Temporary pointer
-  size_t	allsize = 0,		// Size of "all" buffer
+  size_t	allsize = 1,		// Size of "all" buffer
 		textlen;		// Length of "text" string
   mmd_t		*current,		// Current node
 		*next;			// Next node

examples/pdf2text.c

@@ -1,17 +1,17 @@
 //
 // PDF to text program for PDFio.
 //
-// Copyright © 2022 by Michael R Sweet.
+// Copyright © 2022-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
 //
 // Usage:
 //
-//   ./pdfiototext FILENAME.pdf > FILENAME.txt
+//   ./pdf2text FILENAME.pdf > FILENAME.txt
 //
 
-#include "pdfio.h"
+#include <pdfio.h>
 #include <string.h>
 
 
@@ -36,16 +36,14 @@ main(int  argc,				// I - Number of command-line arguments
   // Verify command-line arguments...
   if (argc != 2)
   {
-    puts("Usage: pdfiototext FILENAME.pdf > FILENAME.txt");
+    puts("Usage: pdf2text FILENAME.pdf > FILENAME.txt");
     return (1);
   }
 
   // Open the PDF file...
-  if ((file = pdfioFileOpen(argv[1], NULL, NULL, NULL, NULL)) == NULL)
+  if ((file = pdfioFileOpen(argv[1], /*password_cb*/NULL, /*password_data*/NULL, /*error_cb*/NULL, /*error_data*/NULL)) == NULL)
     return (1);
 
-//  printf("%s: %u pages\n", argv[1], (unsigned)pdfioFileGetNumPages(file));
-
   // Try grabbing content from all of the pages...
   for (i = 0, num_pages = pdfioFileGetNumPages(file); i < num_pages; i ++)
   {
@@ -54,29 +52,28 @@ main(int  argc,				// I - Number of command-line arguments
 
     num_streams = pdfioPageGetNumStreams(obj);
 
-//    printf("%s: page%u=%p, num_streams=%u\n", argv[1], (unsigned)i, obj, (unsigned)num_streams);
-
     for (j = 0; j < num_streams; j ++)
     {
       if ((st = pdfioPageOpenStream(obj, j, true)) == NULL)
 	continue;
 
-//      printf("%s: page%u st%u=%p\n", argv[1], (unsigned)i, (unsigned)j, st);
-
+      // Read PDF tokens from the page stream...
       first = true;
       while (pdfioStreamGetToken(st, buffer, sizeof(buffer)))
       {
 	if (buffer[0] == '(')
 	{
+          // Text string using an 8-bit encoding
 	  if (first)
 	    first = false;
-	  else
+	  else if (buffer[1] != ' ')
 	    putchar(' ');
 
 	  fputs(buffer + 1, stdout);
 	}
 	else if (!strcmp(buffer, "Td") || !strcmp(buffer, "TD") || !strcmp(buffer, "T*") || !strcmp(buffer, "\'") || !strcmp(buffer, "\""))
 	{
+	  // Text operators that advance to the next line in the block
 	  putchar('\n');
 	  first = true;
 	}

examples/pdfioinfo.c

@@ -0,0 +1,65 @@
+//
+// PDF metadata example for PDFio.
+//
+// Copyright © 2023-2024 by Michael R Sweet.
+//
+// Licensed under Apache License v2.0.  See the file "LICENSE" for more
+// information.
+//
+// Usage:
+//
+//   ./pdfioinfo FILENAME.pdf
+//
+
+#include <pdfio.h>
+#include <time.h>
+
+
+//
+// 'main()' - Open a PDF file and show its metadata.
+//
+
+int					// O - Exit status
+main(int  argc,				// I - Number of command-line arguments
+     char *argv[])			// Command-line arguments
+{
+  const char	*filename;		// PDF filename
+  pdfio_file_t	*pdf;			// PDF file
+  time_t	creation_date;		// Creation date
+  struct tm	*creation_tm;		// Creation date/time information
+  char		creation_text[256];	// Creation date/time as a string
+
+
+  // Get the filename from the command-line...
+  if (argc != 2)
+  {
+    fputs("Usage: ./pdfioinfo FILENAME.pdf\n", stderr);
+    return (1);
+  }
+
+  filename = argv[1];
+
+  // Open the PDF file with the default callbacks...
+  pdf = pdfioFileOpen(filename, /*password_cb*/NULL,
+                      /*password_cbdata*/NULL, /*error_cb*/NULL,
+                      /*error_cbdata*/NULL);
+  if (pdf == NULL)
+    return (1);
+
+  // Get the creation date and convert to a string...
+  creation_date = pdfioFileGetCreationDate(pdf);
+  creation_tm   = localtime(&creation_date);
+  strftime(creation_text, sizeof(creation_text), "%c", creation_tm);
+
+  // Print file information to stdout...
+  printf("%s:\n", filename);
+  printf("         Title: %s\n", pdfioFileGetTitle(pdf));
+  printf("        Author: %s\n", pdfioFileGetAuthor(pdf));
+  printf("    Created On: %s\n", creation_text);
+  printf("  Number Pages: %u\n", (unsigned)pdfioFileGetNumPages(pdf));
+
+  // Close the PDF file...
+  pdfioFileClose(pdf);
+
+  return (0);
+}

pdfio-base-font-widths.h

@@ -284,7 +284,7 @@ static short times_roman_widths[256] =
 };
 
 
-static short zapf_dingbats_widths[256] =
+static short zapfdingbats_widths[256] =
 {
   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

pdfio-content.c

@@ -1132,7 +1132,7 @@ pdfioContentTextMeasure(
 	  }
 
 	  if (i < (sizeof(_pdfio_cp1252) / sizeof(_pdfio_cp1252[0])))
-	    ch = i + 0x80;		// Extra characters from 0x80 to 0x9f
+	    ch = (int)(i + 0x80);	// Extra characters from 0x80 to 0x9f
 	  else
 	    ch = '?';			// Unsupported chars map to ?
 	}
@@ -1171,8 +1171,8 @@ pdfioContentTextMeasure(
       widths = times_italic_widths;
     else if (!strcmp(basefont, "Times-Roman"))
       widths = times_roman_widths;
-    else if (!strcmp(basefont, "Zapf-Dingbats"))
-      widths = zapf_dingbats_widths;
+    else if (!strcmp(basefont, "ZapfDingbats"))
+      widths = zapfdingbats_widths;
     else
       return (0.0);
 

pdfio-value.c

@@ -755,6 +755,8 @@ get_date_time(const char *s)		// I - PDF date/time value
   int		offset;			// Date offset
 
 
+  PDFIO_DEBUG("get_date_time(s=\"%s\")\n", s);
+
   // Possible date value of the form:
   //
   //   (D:YYYYMMDDhhmmssZ)
@@ -772,10 +774,12 @@ get_date_time(const char *s)		// I - PDF date/time value
   {
     if (s[i] == 'Z')
     {
+      // UTC...
       i ++;
     }
     else if (s[i] == '-' || s[i] == '+')
     {
+      // Timezone offset from UTC...
       if (isdigit(s[i + 1] & 255) && isdigit(s[i + 2] & 255) && s[i + 3] == '\'' && isdigit(s[i + 4] & 255) && isdigit(s[i + 5] & 255))
       {
 	i += 6;
@@ -783,6 +787,11 @@ get_date_time(const char *s)		// I - PDF date/time value
 	  i ++;
       }
     }
+    else if (!s[i])
+    {
+      // Missing zone info, invalid date string...
+      return (0);
+    }
   }
 
   if (s[i])

pdfio.xcodeproj/project.pbxproj

@@ -3,7 +3,7 @@
 	archiveVersion = 1;
 	classes = {
 	};
-	objectVersion = 50;
+	objectVersion = 54;
 	objects = {
 
 /* Begin PBXBuildFile section */
@@ -31,6 +31,7 @@
 		27F2F0612710BE92008ECD36 /* pdfio-rc4.c in Sources */ = {isa = PBXBuildFile; fileRef = 27F2F05E2710BE92008ECD36 /* pdfio-rc4.c */; };
 		27F2F0622710BE92008ECD36 /* pdfio-crypto.c in Sources */ = {isa = PBXBuildFile; fileRef = 27F2F05F2710BE92008ECD36 /* pdfio-crypto.c */; };
 		27F2F0642711243D008ECD36 /* pdfio-sha256.c in Sources */ = {isa = PBXBuildFile; fileRef = 27F2F0632711243D008ECD36 /* pdfio-sha256.c */; };
+		27FCBDE42D19F9B300485EEE /* pdfio-base-font-widths.h in Headers */ = {isa = PBXBuildFile; fileRef = 27FCBDE32D19F9B300485EEE /* pdfio-base-font-widths.h */; };
 /* End PBXBuildFile section */
 
 /* Begin PBXContainerItemProxy section */
@@ -89,6 +90,7 @@
 		27F2F05E2710BE92008ECD36 /* pdfio-rc4.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = "pdfio-rc4.c"; sourceTree = "<group>"; };
 		27F2F05F2710BE92008ECD36 /* pdfio-crypto.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = "pdfio-crypto.c"; sourceTree = "<group>"; };
 		27F2F0632711243D008ECD36 /* pdfio-sha256.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = "pdfio-sha256.c"; sourceTree = "<group>"; };
+		27FCBDE32D19F9B300485EEE /* pdfio-base-font-widths.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = "pdfio-base-font-widths.h"; sourceTree = "<group>"; };
 /* End PBXFileReference section */
 
 /* Begin PBXFrameworksBuildPhase section */
@@ -162,6 +164,7 @@
 			children = (
 				27CF90432711DFFE00E50FE4 /* pdfio-aes.c */,
 				273440BA263D727800FBFD63 /* pdfio-array.c */,
+				27FCBDE32D19F9B300485EEE /* pdfio-base-font-widths.h */,
 				273440BB263D727800FBFD63 /* pdfio-common.c */,
 				271EA703265B2B1000ACDD39 /* pdfio-content.c */,
 				27F2F05F2710BE92008ECD36 /* pdfio-crypto.c */,
@@ -205,6 +208,7 @@
 			isa = PBXHeadersBuildPhase;
 			buildActionMask = 2147483647;
 			files = (
+				27FCBDE42D19F9B300485EEE /* pdfio-base-font-widths.h in Headers */,
 				273440CC263D727800FBFD63 /* pdfio.h in Headers */,
 				271EA706265B2B1000ACDD39 /* pdfio-content.h in Headers */,
 				273440C3263D727800FBFD63 /* pdfio-private.h in Headers */,
@@ -256,7 +260,8 @@
 		273440A8263D6FE200FBFD63 /* Project object */ = {
 			isa = PBXProject;
 			attributes = {
-				LastUpgradeCheck = 1300;
+				BuildIndependentTargetsInParallel = YES;
+				LastUpgradeCheck = 1600;
 				TargetAttributes = {
 					273440AF263D6FE200FBFD63 = {
 						CreatedOnToolsVersion = 12.5;
@@ -373,9 +378,11 @@
 				CODE_SIGN_IDENTITY = "Apple Development";
 				COPY_PHASE_STRIP = NO;
 				CURRENT_PROJECT_VERSION = 1.1.2;
+				DEAD_CODE_STRIPPING = YES;
 				DEBUG_INFORMATION_FORMAT = dwarf;
 				ENABLE_STRICT_OBJC_MSGSEND = YES;
 				ENABLE_TESTABILITY = YES;
+				ENABLE_USER_SCRIPT_SANDBOXING = YES;
 				GCC_C_LANGUAGE_STANDARD = gnu11;
 				GCC_NO_COMMON_BLOCKS = YES;
 				GCC_PREPROCESSOR_DEFINITIONS = (
@@ -450,15 +457,15 @@
 				CODE_SIGN_IDENTITY = "Apple Development";
 				COPY_PHASE_STRIP = NO;
 				CURRENT_PROJECT_VERSION = 1.1.2;
+				DEAD_CODE_STRIPPING = YES;
 				DEBUG_INFORMATION_FORMAT = "dwarf-with-dsym";
 				ENABLE_HARDENED_RUNTIME = YES;
 				ENABLE_NS_ASSERTIONS = NO;
 				ENABLE_STRICT_OBJC_MSGSEND = YES;
+				ENABLE_USER_SCRIPT_SANDBOXING = YES;
 				GCC_C_LANGUAGE_STANDARD = gnu11;
 				GCC_NO_COMMON_BLOCKS = YES;
-				GCC_PREPROCESSOR_DEFINITIONS = (
-					"$(inherited)",
-				);
+				GCC_PREPROCESSOR_DEFINITIONS = "$(inherited)";
 				GCC_TREAT_IMPLICIT_FUNCTION_DECLARATIONS_AS_ERRORS = YES;
 				GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
 				GCC_WARN_ABOUT_MISSING_FIELD_INITIALIZERS = YES;
@@ -486,6 +493,7 @@
 			isa = XCBuildConfiguration;
 			buildSettings = {
 				CODE_SIGN_STYLE = Automatic;
+				DEAD_CODE_STRIPPING = YES;
 				DEVELOPMENT_TEAM = RU58A2256H;
 				EXECUTABLE_PREFIX = lib;
 				PRODUCT_NAME = "$(TARGET_NAME)";
@@ -497,6 +505,7 @@
 			isa = XCBuildConfiguration;
 			buildSettings = {
 				CODE_SIGN_STYLE = Automatic;
+				DEAD_CODE_STRIPPING = YES;
 				DEVELOPMENT_TEAM = RU58A2256H;
 				EXECUTABLE_PREFIX = lib;
 				PRODUCT_NAME = "$(TARGET_NAME)";
@@ -509,6 +518,7 @@
 			buildSettings = {
 				CODE_SIGN_IDENTITY = "-";
 				CODE_SIGN_STYLE = Automatic;
+				DEAD_CODE_STRIPPING = YES;
 				DEVELOPMENT_TEAM = "";
 				ENABLE_HARDENED_RUNTIME = YES;
 				GCC_DYNAMIC_NO_PIC = NO;
@@ -525,6 +535,7 @@
 			buildSettings = {
 				CODE_SIGN_IDENTITY = "-";
 				CODE_SIGN_STYLE = Automatic;
+				DEAD_CODE_STRIPPING = YES;
 				DEVELOPMENT_TEAM = "";
 				ENABLE_HARDENED_RUNTIME = YES;
 				MACOSX_DEPLOYMENT_TARGET = 11.0;

pdfio_native.nuspec

@@ -3,7 +3,7 @@
     <metadata>
         <id>pdfio_native</id>
         <title>PDFio Library for VS2019+</title>
-        <version>1.3.2</version>
+        <version>1.4.0</version>
         <authors>Michael R Sweet</authors>
         <owners>michaelrsweet</owners>
         <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>
@@ -16,7 +16,7 @@
         <copyright>Copyright © 2019-2024 by Michael R Sweet</copyright>
         <tags>pdf file native</tags>
 	<dependencies>
-	    <dependency id="pdfio_native.redist" version="1.3.2" />
+	    <dependency id="pdfio_native.redist" version="1.4.0" />
 	    <dependency id="zlib_native.redist" version="1.2.11" />
 	</dependencies>
     </metadata>

pdfio_native.redist.nuspec

@@ -3,7 +3,7 @@
     <metadata>
         <id>pdfio_native.redist</id>
         <title>PDFio Library for VS2019+</title>
-        <version>1.3.2</version>
+        <version>1.4.0</version>
         <authors>Michael R Sweet</authors>
         <owners>michaelrsweet</owners>
         <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>