Update pdfio.md

addition of lines requeested

CHANGES.md

@@ -2,16 +2,24 @@ Changes in PDFio
 ================
 
 
-v1.3.1 (August 5, 2024)
+v1.3.2 - 2024-08-15
------------------------
+-------------------
+
+- Added some more sanity checks to the TrueType font reader.
+- Updated documentation (Issue #77)
+- Fixed an issue when opening certain encrypted PDF files (Issue #62)
+
+
+v1.3.1 - 2024-08-05
+-------------------
 
 - CVE 2024-42358: Updated TrueType font reader to avoid large memory
   allocations.
 - Fixed some documentation errors and added examples (Issue #68, Issue #69)
 
 
-v1.3.0 (June 28, 2024)
+v1.3.0 - 2024-06-28
-----------------------
+-------------------
 
 - Added `pdfioFileGetCatalog` API for accessing the root/catalog object of a
   PDF file (Issue #67)
@@ -21,8 +29,8 @@ v1.3.0 (June 28, 2024)
 - Optimized string pool code.
 
 
-v1.2.0 (January 24, 2024)
+v1.2.0 - 2024-01-24
--------------------------
+-------------------
 
 - Now use autoconf to configure the PDFio sources (Issue #54)
 - Added `pdfioFileCreateNumberObj` and `pdfioFileCreateStringObj` functions
@@ -45,8 +53,8 @@ v1.2.0 (January 24, 2024)
   65536 in the xref table (Issue #59)
 
 
-v1.1.4 (December 3, 2023)
+v1.1.4 - 2023-12-03
--------------------------
+-------------------
 
 - Fixed detection of encrypted strings that are too short (Issue #52)
 - Fixed a TrueType CMAP decoding bug.
@@ -54,15 +62,15 @@ v1.1.4 (December 3, 2023)
 - Added a ToUnicode map for Unicode text to support text copying.
 
 
-v1.1.3 (November 15, 2023)
+v1.1.3 - 2023-11-15
---------------------------
+-------------------
 
 - Fixed Unicode font support (Issue #16)
 - Fixed missing initializer for 40-bit RC4 encryption (Issue #51)
 
 
-v1.1.2 (October 10, 2023)
+v1.1.2 - 2023-10-10
--------------------------
+-------------------
 
 - Updated `pdfioContentSetDashPattern` to support setting a solid (0 length)
   dash pattern (Issue #41)
@@ -77,15 +85,15 @@ v1.1.2 (October 10, 2023)
   (Issue #48)
 
 
-v1.1.1 (March 20, 2023)
+v1.1.1 - 2023-03-20
------------------------
+-------------------
 
 - CVE-2023-28428: Fixed a potential denial-of-service with corrupt PDF files.
 - Fixed a few build issues.
 
 
-v1.1.0 (February 6, 2023)
+v1.1.0 - 2023-02-06
--------------------------
+-------------------
 
 - CVE-2023-24808: Fixed a potential denial-of-service with corrupt PDF files.
 - Added `pdfioFileCreateTemporary` function (Issue #29)
@@ -99,28 +107,28 @@ v1.1.0 (February 6, 2023)
 - Fixed `pdfioContentMatrixRotate` function.
 
 
-v1.0.1 (March 2, 2022)
+v1.0.1 - 2022-03-02
-----------------------
+-------------------
 
 - Added missing `pdfioPageGetNumStreams` and `pdfioPageOpenStream` functions.
 - Added demo pdfiototext utility.
 - Fixed bug in `pdfioStreamGetToken`.
 
 
-v1.0.0 (December 14, 2021)
+v1.0.0 - 2021-12-14
---------------------------
+-------------------
 
 - First stable release.
 
 
-v1.0rc1 (November 30, 2021)
+v1.0rc1 - 2021-11-30
----------------------------
+--------------------
 
 - Fixed a few stack/buffer overflow bugs discovered via fuzzing.
 
 
-v1.0b2 (November 7, 2021)
+v1.0b2 - 2021-11-07
--------------------------
+-------------------
 
 - Added `pdfioFileCreateOutput` API to support streaming output of PDF
   (Issue #21)
@@ -131,7 +139,7 @@ v1.0b2 (November 7, 2021)
 - Fixed some issues identified by a Coverity scan.
 
 
-v1.0b1 (August 30, 2021)
+v1.0b1 - 2021-08-30
-------------------------
+-------------------
 
 - Initial release

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for pdfio 1.3.1.
+# Generated by GNU Autoconf 2.71 for pdfio 1.3.2.
 #
 # Report bugs to <https://github.com/michaelrsweet/pdfio/issues>.
 #
@@ -610,8 +610,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='pdfio'
 PACKAGE_TARNAME='pdfio'
-PACKAGE_VERSION='1.3.1'
+PACKAGE_VERSION='1.3.2'
-PACKAGE_STRING='pdfio 1.3.1'
+PACKAGE_STRING='pdfio 1.3.2'
 PACKAGE_BUGREPORT='https://github.com/michaelrsweet/pdfio/issues'
 PACKAGE_URL='https://www.msweet.org/pdfio'
 
@@ -1293,7 +1293,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures pdfio 1.3.1 to adapt to many kinds of systems.
+\`configure' configures pdfio 1.3.2 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1359,7 +1359,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of pdfio 1.3.1:";;
+     short | recursive ) echo "Configuration of pdfio 1.3.2:";;
    esac
   cat <<\_ACEOF
 
@@ -1456,7 +1456,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-pdfio configure 1.3.1
+pdfio configure 1.3.2
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -1612,7 +1612,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by pdfio $as_me 1.3.1, which was
+It was created by pdfio $as_me 1.3.2, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -2368,9 +2368,9 @@ ac_compiler_gnu=$ac_cv_c_compiler_gnu
 
 
 
-PDFIO_VERSION="1.3.1"
+PDFIO_VERSION="1.3.2"
-PDFIO_VERSION_MAJOR="`echo 1.3.1 | awk -F. '{print $1}'`"
+PDFIO_VERSION_MAJOR="`echo 1.3.2 | awk -F. '{print $1}'`"
-PDFIO_VERSION_MINOR="`echo 1.3.1 | awk -F. '{printf("%d\n",$2);}'`"
+PDFIO_VERSION_MINOR="`echo 1.3.2 | awk -F. '{printf("%d\n",$2);}'`"
 
 
 
@@ -4935,7 +4935,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by pdfio $as_me 1.3.1, which was
+This file was extended by pdfio $as_me 1.3.2, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -4991,7 +4991,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-pdfio config.status 1.3.1
+pdfio config.status 1.3.2
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 

configure.ac

@@ -21,7 +21,7 @@ AC_PREREQ([2.70])
 
 
 dnl Package name and version...
-AC_INIT([pdfio], [1.3.1], [https://github.com/michaelrsweet/pdfio/issues], [pdfio], [https://www.msweet.org/pdfio])
+AC_INIT([pdfio], [1.3.2], [https://github.com/michaelrsweet/pdfio/issues], [pdfio], [https://www.msweet.org/pdfio])
 
 PDFIO_VERSION="AC_PACKAGE_VERSION"
 PDFIO_VERSION_MAJOR="`echo AC_PACKAGE_VERSION | awk -F. '{print $1}'`"

doc/pdfio.3

@@ -1,4 +1,4 @@
-.TH pdfio 3 "pdf read/write library" "2024-08-05" "pdf read/write library"
+.TH pdfio 3 "pdf read/write library" "2024-10-09" "pdf read/write library"
 .SH NAME
 pdfio \- pdf read/write library
 .SH Introduction
@@ -218,7 +218,90 @@ Each PDF file contains one or more pages. The pdfioFileGetNumPages function retu
     }
 .fi
 .PP
-Each page is represented by a "page tree" object (what pdfioFileGetPage returns) that specifies information about the page and one or more "content" objects that contain the images, fonts, text, and graphics that appear on the page. Use the pdfioPageGetNumStreams and pdfioPageOpenStream functions to access the content streams for each page.
+Each page is represented by a "page tree" object (what pdfioFileGetPage returns) that specifies information about the page and one or more "content" objects that contain the images, fonts, text, and graphics that appear on the page. Use the pdfioPageGetNumStreams and pdfioPageOpenStream functions to access the content streams for each page, and pdfioObjGetDict to get the associated page object dictionary. For example, if you want to display the media and crop boxes for a given page:
+.nf
+
+    pdfio_file_t  *pdf;             // PDF file
+    size_t        i;                // Looping var
+    size_t        count;            // Number of pages
+    pdfio_obj_t   *page;            // Current page
+    pdfio_dict_t  *dict;            // Current page dictionary
+    pdfio_array_t *media_box;       // MediaBox array
+    double        media_values[4];  // MediaBox values
+    pdfio_array_t *crop_box;        // CropBox array
+    double        crop_values[4];   // CropBox values
+    
+    // Iterate the pages in the PDF file
+    for (i = 0, count = pdfioFileGetNumPages(pdf); i < count; i ++)
+    {
+      page = pdfioFileGetPage(pdf, i);
+      dict = pdfioObjGetDict(page);
+    
+      media_box       = pdfioDictGetArray(dict, "MediaBox");
+      media_values[0] = pdfioArrayGetNumber(media_box, 0);
+      media_values[1] = pdfioArrayGetNumber(media_box, 1);
+      media_values[2] = pdfioArrayGetNumber(media_box, 2);
+      media_values[3] = pdfioArrayGetNumber(media_box, 3);
+    
+      crop_box       = pdfioDictGetArray(dict, "CropBox");
+      crop_values[0] = pdfioArrayGetNumber(crop_box, 0);
+      crop_values[1] = pdfioArrayGetNumber(crop_box, 1);
+      crop_values[2] = pdfioArrayGetNumber(crop_box, 2);
+      crop_values[3] = pdfioArrayGetNumber(crop_box, 3);
+    
+      printf("Page %u: MediaBox=[%g %g %g %g], CropBox=[%g %g %g %g]\\n",
+             (unsigned)(i + 1),
+             media_values[0], media_values[1], media_values[2], media_values[3],
+             crop_values[0], crop_values[1], crop_values[2], crop_values[3]);
+    }
+.fi
+.PP
+Page object dictionaries have several (mostly optional) key/value pairs, including:
+.IP \(bu 5
+.PP
+"Annots": An array of annotation dictionaries for the page; use pdfioDictGetArray to get the array
+
+.IP \(bu 5
+.PP
+"CropBox": The crop box as an array of four numbers for the left, bottom, right, and top coordinates of the target media; use pdfioDictGetArray to get a pointer to the array of numbers
+
+.IP \(bu 5
+.PP
+"Dur": The number of seconds the page should be displayed; use pdfioDictGetNumber to get the page duration value
+
+.IP \(bu 5
+.PP
+"Group": The dictionary of transparency group values for the page; use pdfioDictGetDict to get a pointer to the resources dictionary
+
+.IP \(bu 5
+.PP
+"LastModified": The date and time when this page was last modified; use pdfioDictGetDate to get the Unix time_t value
+
+.IP \(bu 5
+.PP
+"Parent": The parent page tree node object for this page; use pdfioDictGetObj to get a pointer to the object
+
+.IP \(bu 5
+.PP
+"MediaBox": The media box as an array of four numbers for the left, bottom, right, and top coordinates of the target media; use pdfioDictGetArray to get a pointer to the array of numbers
+
+.IP \(bu 5
+.PP
+"Resources": The dictionary of resources for the page; use pdfioDictGetDict to get a pointer to the resources dictionary
+
+.IP \(bu 5
+.PP
+"Rotate": A number indicating the number of degrees of counter\-clockwise rotation to apply to the page when viewing; use pdfioDictGetNumber to get the rotation angle
+
+.IP \(bu 5
+.PP
+"Thumb": A thumbnail image object for the page; use pdfioDictGetObj to get a pointer to the thumbnail image object
+
+.IP \(bu 5
+.PP
+"Trans": The page transition dictionary; use pdfioDictGetDict to get a pointer to the dictionary
+
+
 .PP
 The pdfioFileClose function closes a PDF file and frees all memory that was used for it:
 .nf
@@ -2869,6 +2952,29 @@ const char * pdfioObjGetSubtype (
     pdfio_obj_t *obj
 );
 .fi
+.PP
+This function returns an object's PDF subtype name, if any.  Common subtype
+names include:
+.PP
+.IP \(bu 5
+"CIDFontType0": A CID Type0 font
+.IP \(bu 5
+"CIDFontType2": A CID TrueType font
+.IP \(bu 5
+"Image": An image or image mask
+.IP \(bu 5
+"Form": A fillable form
+.IP \(bu 5
+"OpenType": An OpenType font
+.IP \(bu 5
+"Type0": A composite font
+.IP \(bu 5
+"Type1": A PostScript Type1 font
+.IP \(bu 5
+"Type3": A PDF Type3 font
+.IP \(bu 5
+"TrueType": A TrueType font</li>
+</ul>
 .SS pdfioObjGetType
 Get an object's type.
 .PP
@@ -2877,6 +2983,27 @@ const char * pdfioObjGetType (
     pdfio_obj_t *obj
 );
 .fi
+.PP
+This function returns an object's PDF type name, if any. Common type names
+include:
+.PP
+.IP \(bu 5
+"CMap": A character map for composite fonts
+.IP \(bu 5
+"Font": An embedded font (\fIpdfioObjGetSubtype\fR will tell you the
+  font format)
+.IP \(bu 5
+"FontDescriptor": A font descriptor
+.IP \(bu 5
+"Page": A (visible) page
+.IP \(bu 5
+"Pages": A page tree node
+.IP \(bu 5
+"Template": An invisible template page
+.IP \(bu 5
+"XObject": An image, image mask, or form (\fIpdfioObjGetSubtype\fR will
+  tell you which)</li>
+</ul>
 .SS pdfioObjOpenStream
 Open an object's (data) stream for reading.
 .PP

doc/pdfio.html

@@ -1,13 +1,13 @@
 <!DOCTYPE html>
 <html lang="en-US">
 <head>
-<title>PDFio Programming Manual v1.3.0</title>
+<title>PDFio Programming Manual v1.3.2</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 © 2021-2024 by Michael R Sweet">
-<meta name="version" content="1.3.0">
+<meta name="version" content="1.3.2">
 <style type="text/css"><!--
 body {
   background: white;
@@ -251,7 +251,7 @@ span.string {
 <body>
 <div class="header">
 <p><img class="title" src="pdfio-512.png"></p>
-<h1 class="title">PDFio Programming Manual v1.3.0</h1>
+<h1 class="title">PDFio Programming Manual v1.3.2</h1>
 <p>Michael R Sweet</p>
 <p>Copyright © 2021-2024 by Michael R Sweet</p>
 </div>
@@ -628,7 +628,66 @@ pdfio_obj_t  *page;  <span class="comment">// Current page</span>
   <span class="comment">// do something with page</span>
 }
 </code></pre>
-<p>Each page is represented by a &quot;page tree&quot; object (what <a href="#pdfioFileGetPage"><code>pdfioFileGetPage</code></a> returns) that specifies information about the page and one or more &quot;content&quot; objects that contain the images, fonts, text, and graphics that appear on the page. Use the <a href="#pdfioPageGetNumStreams"><code>pdfioPageGetNumStreams</code></a> and <a href="#pdfioPageOpenStream"><code>pdfioPageOpenStream</code></a> functions to access the content streams for each page.</p>
+<p>Each page is represented by a &quot;page tree&quot; object (what <a href="#pdfioFileGetPage"><code>pdfioFileGetPage</code></a> returns) that specifies information about the page and one or more &quot;content&quot; objects that contain the images, fonts, text, and graphics that appear on the page. Use the <a href="#pdfioPageGetNumStreams"><code>pdfioPageGetNumStreams</code></a> and <a href="#pdfioPageOpenStream"><code>pdfioPageOpenStream</code></a> functions to access the content streams for each page, and <a href="#pdfioObjGetDict"><code>pdfioObjGetDict</code></a> to get the associated page object dictionary. For example, if you want to display the media and crop boxes for a given page:</p>
+<pre><code class="language-c">pdfio_file_t  *pdf;             <span class="comment">// PDF file</span>
+size_t        i;                <span class="comment">// Looping var</span>
+size_t        count;            <span class="comment">// Number of pages</span>
+pdfio_obj_t   *page;            <span class="comment">// Current page</span>
+pdfio_dict_t  *dict;            <span class="comment">// Current page dictionary</span>
+pdfio_array_t *media_box;       <span class="comment">// MediaBox array</span>
+<span class="reserved">double</span>        media_values[<span class="number">4</span>];  <span class="comment">// MediaBox values</span>
+pdfio_array_t *crop_box;        <span class="comment">// CropBox array</span>
+<span class="reserved">double</span>        crop_values[<span class="number">4</span>];   <span class="comment">// CropBox values</span>
+
+<span class="comment">// Iterate the pages in the PDF file</span>
+<span class="reserved">for</span> (i = <span class="number">0</span>, count = pdfioFileGetNumPages(pdf); i &lt; count; i ++)
+{
+  page = pdfioFileGetPage(pdf, i);
+  dict = pdfioObjGetDict(page);
+
+  media_box       = pdfioDictGetArray(dict, <span class="string">&quot;MediaBox&quot;</span>);
+  media_values[<span class="number">0</span>] = pdfioArrayGetNumber(media_box, <span class="number">0</span>);
+  media_values[<span class="number">1</span>] = pdfioArrayGetNumber(media_box, <span class="number">1</span>);
+  media_values[<span class="number">2</span>] = pdfioArrayGetNumber(media_box, <span class="number">2</span>);
+  media_values[<span class="number">3</span>] = pdfioArrayGetNumber(media_box, <span class="number">3</span>);
+
+  crop_box       = pdfioDictGetArray(dict, <span class="string">&quot;CropBox&quot;</span>);
+  crop_values[<span class="number">0</span>] = pdfioArrayGetNumber(crop_box, <span class="number">0</span>);
+  crop_values[<span class="number">1</span>] = pdfioArrayGetNumber(crop_box, <span class="number">1</span>);
+  crop_values[<span class="number">2</span>] = pdfioArrayGetNumber(crop_box, <span class="number">2</span>);
+  crop_values[<span class="number">3</span>] = pdfioArrayGetNumber(crop_box, <span class="number">3</span>);
+
+  printf(<span class="string">&quot;Page %u: MediaBox=[%g %g %g %g], CropBox=[%g %g %g %g]\n&quot;</span>,
+         (<span class="reserved">unsigned</span>)(i + <span class="number">1</span>),
+         media_values[<span class="number">0</span>], media_values[<span class="number">1</span>], media_values[<span class="number">2</span>], media_values[<span class="number">3</span>],
+         crop_values[<span class="number">0</span>], crop_values[<span class="number">1</span>], crop_values[<span class="number">2</span>], crop_values[<span class="number">3</span>]);
+}
+</code></pre>
+<p>Page object dictionaries have several (mostly optional) key/value pairs, including:</p>
+<ul>
+<li><p>&quot;Annots&quot;: An array of annotation dictionaries for the page; use <a href="#pdfioDictGetArray"><code>pdfioDictGetArray</code></a> to get the array</p>
+</li>
+<li><p>&quot;CropBox&quot;: The crop box as an array of four numbers for the left, bottom, right, and top coordinates of the target media; use <a href="#pdfioDictGetArray"><code>pdfioDictGetArray</code></a> to get a pointer to the array of numbers</p>
+</li>
+<li><p>&quot;Dur&quot;: The number of seconds the page should be displayed; use <a href="#pdfioDictGetNumber"><code>pdfioDictGetNumber</code></a> to get the page duration value</p>
+</li>
+<li><p>&quot;Group&quot;: The dictionary of transparency group values for the page; use <a href="#pdfioDictGetDict"><code>pdfioDictGetDict</code></a> to get a pointer to the resources dictionary</p>
+</li>
+<li><p>&quot;LastModified&quot;: The date and time when this page was last modified; use <a href="#pdfioDictGetDate"><code>pdfioDictGetDate</code></a> to get the Unix <code>time_t</code> value</p>
+</li>
+<li><p>&quot;Parent&quot;: The parent page tree node object for this page; use <a href="#pdfioDictGetObj"><code>pdfioDictGetObj</code></a> to get a pointer to the object</p>
+</li>
+<li><p>&quot;MediaBox&quot;: The media box as an array of four numbers for the left, bottom, right, and top coordinates of the target media; use <a href="#pdfioDictGetArray"><code>pdfioDictGetArray</code></a> to get a pointer to the array of numbers</p>
+</li>
+<li><p>&quot;Resources&quot;: The dictionary of resources for the page; use <a href="#pdfioDictGetDict"><code>pdfioDictGetDict</code></a> to get a pointer to the resources dictionary</p>
+</li>
+<li><p>&quot;Rotate&quot;: A number indicating the number of degrees of counter-clockwise rotation to apply to the page when viewing; use <a href="#pdfioDictGetNumber"><code>pdfioDictGetNumber</code></a> to get the rotation angle</p>
+</li>
+<li><p>&quot;Thumb&quot;: A thumbnail image object for the page; use <a href="#pdfioDictGetObj"><code>pdfioDictGetObj</code></a> to get a pointer to the thumbnail image object</p>
+</li>
+<li><p>&quot;Trans&quot;: The page transition dictionary; use <a href="#pdfioDictGetDict"><code>pdfioDictGetDict</code></a> to get a pointer to the dictionary</p>
+</li>
+</ul>
 <p>The <a href="#pdfioFileClose"><code>pdfioFileClose</code></a> function closes a PDF file and frees all memory that was used for it:</p>
 <pre><code class="language-c">pdfioFileClose(pdf);
 </code></pre>
@@ -3490,7 +3549,30 @@ size_t pdfioObjGetNumber(<a href="#pdfio_obj_t">pdfio_obj_t</a> *obj);</p>
 <td class="description">Object</td></tr>
 </tbody></table>
 <h4 class="returnvalue">Return Value</h4>
-<p class="description">Object subtype</p>
+<p class="description">Object subtype name or <code>NULL</code> for none</p>
+<h4 class="discussion">Discussion</h4>
+<p class="discussion">This function returns an object's PDF subtype name, if any.  Common subtype
+names include:
+
+</p><ul>
+<li>&quot;CIDFontType0&quot;: A CID Type0 font
+</li>
+<li>&quot;CIDFontType2&quot;: A CID TrueType font
+</li>
+<li>&quot;Image&quot;: An image or image mask
+</li>
+<li>&quot;Form&quot;: A fillable form
+</li>
+<li>&quot;OpenType&quot;: An OpenType font
+</li>
+<li>&quot;Type0&quot;: A composite font
+</li>
+<li>&quot;Type1&quot;: A PostScript Type1 font
+</li>
+<li>&quot;Type3&quot;: A PDF Type3 font
+</li>
+<li>&quot;TrueType&quot;: A TrueType font</li>
+</ul>
 <h3 class="function"><a id="pdfioObjGetType">pdfioObjGetType</a></h3>
 <p class="description">Get an object's type.</p>
 <p class="code">
@@ -3501,7 +3583,28 @@ size_t pdfioObjGetNumber(<a href="#pdfio_obj_t">pdfio_obj_t</a> *obj);</p>
 <td class="description">Object</td></tr>
 </tbody></table>
 <h4 class="returnvalue">Return Value</h4>
-<p class="description">Object type</p>
+<p class="description">Object type name or <code>NULL</code> for none</p>
+<h4 class="discussion">Discussion</h4>
+<p class="discussion">This function returns an object's PDF type name, if any. Common type names
+include:
+
+</p><ul>
+<li>&quot;CMap&quot;: A character map for composite fonts
+</li>
+<li>&quot;Font&quot;: An embedded font (<a href="#pdfioObjGetSubtype"><code>pdfioObjGetSubtype</code></a> will tell you the
+  font format)
+</li>
+<li>&quot;FontDescriptor&quot;: A font descriptor
+</li>
+<li>&quot;Page&quot;: A (visible) page
+</li>
+<li>&quot;Pages&quot;: A page tree node
+</li>
+<li>&quot;Template&quot;: An invisible template page
+</li>
+<li>&quot;XObject&quot;: An image, image mask, or form (<a href="#pdfioObjGetSubtype"><code>pdfioObjGetSubtype</code></a> will
+  tell you which)</li>
+</ul>
 <h3 class="function"><a id="pdfioObjOpenStream">pdfioObjOpenStream</a></h3>
 <p class="description">Open an object's (data) stream for reading.</p>
 <p class="code">

doc/pdfio.md

@@ -118,6 +118,159 @@ that are defined in a separate header file:
 ```c
 #include <pdfio-content.h>
 ```
+Understanding PDF Files
+-----------------------
+
+A PDF file provides data and commands for displaying pages of graphics and text, 
+and is structured in a way that allows it to be displayed in the same way across 
+multiple devices and platforms.  
+The following is a PDF which shows "Hello, World!" on one page:
+```
+%PDF-1.0                              %Header starts here
+%âãÏÓ
+1 0 obj                               %Body starts here
+<<
+/Kids [2 0 R]
+/Count 1
+/Type /Pages
+>>
+endobj
+2 0 obj
+<<
+/Rotate 0
+/Parent 1 0 R
+/Resources 3 0 R
+/MediaBox [0 0 612 792]
+/Contents [4 0 R]/Type /Page
+>>
+endobj
+3 0 obj
+<<
+/Font
+<<
+/F0
+<<
+/BaseFont /Times-Italic
+/Subtype /Type1
+/Type /Font
+>>
+>>
+>>
+endobj
+4 0 obj
+<<
+/Length 65
+>>
+stream
+1. 0. 0. 1. 50. 700. cm
+BT
+  /F0 36. Tf
+  (Hello, World!) Tj
+ET
+endstream
+endobj
+5 0 obj
+<<
+/Pages 1 0 R
+/Type /Catalog
+>>
+endobj
+xref                               %Cross-reference table starts here
+0 6
+0000000000 65535 f
+0000000015 00000 n
+0000000074 00000 n
+0000000192 00000 n
+0000000291 00000 n
+0000000409 00000 n
+trailer                            %Trailer starts here
+<<
+/Root 5 0 R
+/Size 6
+>>
+startxref
+459
+%%EOF
+```
+
+### Header
+This is the first line of a PDF File. This specifies the version of PDF Format used.  
+For Example: '%PDF-1.0'
+
+Since PDF files almost always contain binary data, they can become corrupted if line 
+endings are changed (for example, if the file is transferred over FTP in text mode). 
+To allow legacy file transfer programs to determine that the file is binary, it is 
+usual to include some bytes withcharacter codes higher than 127 in the header.
+- For example: %âãÏÓ
+- The percent sign indicates another header line, the other few bytes are arbitrary
+character codes in excess of 127. So, the whole header in our example is:
+
+```
+%PDF-1.0  
+%âãÏÓ
+```
+
+### Body
+The file body consists of a sequence of objects, each preceded by an object number, 
+generation number, and the obj keyword on one line, and followed by the endobj keyword 
+on another. For Example:
+
+```  
+1 0 obj
+<<
+/Kids [2 0 R]
+/Count 1
+/Type /Pages
+>>
+endobj
+```
+
+Here, the object number is 1, and the generation number is 0 (it almost always is). 
+The content for object 1 is in between the two lines 1 0 obj and endobj.  
+In this case, it’s the dictionary <</Kids [2 0 R] /Count 1 /Type /Pages>>
+
+### Cross-Reference Table
+The cross-reference table lists the byte offset of each object in the file body.
+This allows random access to objects, meaning they don't have to be read in order.  
+Objects that are not used are never read, making the process efficient.
+Operations like counting the number of pages in a PDF document are fast, even in large files.
+Each object has an object number and a generation number.
+  - Generation numbers are used when a cross-reference table entry is reused.
+  - For simplicity, we will assume generation numbers to be always zero and ignore them.  
+The cross-reference table consists of:
+  - Header line that indicates the number of entries.
+  - Special entry (the first entry).
+  - One line for each of the object in the file body.
+
+```
+0 6                  %Six entries in table, starting at 0
+0000000000 65535 f   %Special entry
+0000000015 00000 n   %Object 1 is at byte offset 15
+0000000074 00000 n   %Object 2 is at byte offset 74
+0000000192 00000 n   %etc...
+0000000291 00000 n  
+0000000409 00000 n   %Object 5 is at byte offset 409
+```
+
+### Trailer
+The first line of the trailer is just the trailer keyword. This is followed by the trailer dictionary, 
+which contains at least the /Size entry (Number of entries in the cross-reference table) 
+and the /Root entry (Object number of the document catalog, which is the root element 
+of the graph of objects in the body).  
+There follows a line with just the startxref keyword, a line with a single number (the byte offset of 
+the start of the cross-reference table within the file), and then the line %%EOF, which signals the 
+end of the PDF file.
+
+```
+trailer          %Trailer keyword
+<<               %The trailer dictinonary
+/Root 5 0 R
+/Size 6
+>>
+startxref        %startxref keyword
+459              %Byte offset of cross-reference table
+%%EOF            %End-of-file marker
+```
 
 
 API Overview
@@ -132,6 +285,7 @@ PDFio exposes several types:
 - `pdfio_stream_t`: An object stream
 
 
+
 Reading PDF Files
 -----------------
 
@@ -202,7 +356,74 @@ Each page is represented by a "page tree" object (what [`pdfioFileGetPage`](@@)
 returns) that specifies information about the page and one or more "content"
 objects that contain the images, fonts, text, and graphics that appear on the
 page.  Use the [`pdfioPageGetNumStreams`](@@) and [`pdfioPageOpenStream`](@@)
-functions to access the content streams for each page.
+functions to access the content streams for each page, and
+[`pdfioObjGetDict`](@@) to get the associated page object dictionary.  For
+example, if you want to display the media and crop boxes for a given page:
+
+```c
+pdfio_file_t  *pdf;             // PDF file
+size_t        i;                // Looping var
+size_t        count;            // Number of pages
+pdfio_obj_t   *page;            // Current page
+pdfio_dict_t  *dict;            // Current page dictionary
+pdfio_array_t *media_box;       // MediaBox array
+double        media_values[4];  // MediaBox values
+pdfio_array_t *crop_box;        // CropBox array
+double        crop_values[4];   // CropBox values
+
+// Iterate the pages in the PDF file
+for (i = 0, count = pdfioFileGetNumPages(pdf); i < count; i ++)
+{
+  page = pdfioFileGetPage(pdf, i);
+  dict = pdfioObjGetDict(page);
+
+  media_box       = pdfioDictGetArray(dict, "MediaBox");
+  media_values[0] = pdfioArrayGetNumber(media_box, 0);
+  media_values[1] = pdfioArrayGetNumber(media_box, 1);
+  media_values[2] = pdfioArrayGetNumber(media_box, 2);
+  media_values[3] = pdfioArrayGetNumber(media_box, 3);
+
+  crop_box       = pdfioDictGetArray(dict, "CropBox");
+  crop_values[0] = pdfioArrayGetNumber(crop_box, 0);
+  crop_values[1] = pdfioArrayGetNumber(crop_box, 1);
+  crop_values[2] = pdfioArrayGetNumber(crop_box, 2);
+  crop_values[3] = pdfioArrayGetNumber(crop_box, 3);
+
+  printf("Page %u: MediaBox=[%g %g %g %g], CropBox=[%g %g %g %g]\n",
+         (unsigned)(i + 1),
+         media_values[0], media_values[1], media_values[2], media_values[3],
+         crop_values[0], crop_values[1], crop_values[2], crop_values[3]);
+}
+```
+
+Page object dictionaries have several (mostly optional) key/value pairs,
+including:
+
+- "Annots": An array of annotation dictionaries for the page; use
+  [`pdfioDictGetArray`](@@) to get the array
+- "CropBox": The crop box as an array of four numbers for the left, bottom,
+  right, and top coordinates of the target media; use [`pdfioDictGetArray`](@@)
+  to get a pointer to the array of numbers
+- "Dur": The number of seconds the page should be displayed; use
+  [`pdfioDictGetNumber`](@@) to get the page duration value
+- "Group": The dictionary of transparency group values for the page; use
+  [`pdfioDictGetDict`](@@) to get a pointer to the resources dictionary
+- "LastModified": The date and time when this page was last modified; use
+  [`pdfioDictGetDate`](@@) to get the Unix `time_t` value
+- "Parent": The parent page tree node object for this page; use
+  [`pdfioDictGetObj`](@@) to get a pointer to the object
+- "MediaBox": The media box as an array of four numbers for the left, bottom,
+  right, and top coordinates of the target media; use [`pdfioDictGetArray`](@@)
+  to get a pointer to the array of numbers
+- "Resources": The dictionary of resources for the page; use
+  [`pdfioDictGetDict`](@@) to get a pointer to the resources dictionary
+- "Rotate": A number indicating the number of degrees of counter-clockwise
+  rotation to apply to the page when viewing; use [`pdfioDictGetNumber`](@@)
+  to get the rotation angle
+- "Thumb": A thumbnail image object for the page; use [`pdfioDictGetObj`](@@)
+  to get a pointer to the thumbnail image object
+- "Trans": The page transition dictionary; use [`pdfioDictGetDict`](@@) to get
+  a pointer to the dictionary
 
 The [`pdfioFileClose`](@@) function closes a PDF file and frees all memory that
 was used for it:

pdfio-array.c

@@ -363,6 +363,9 @@ _pdfioArrayDebug(pdfio_array_t *a,	// I - Array
   _pdfio_value_t	*v;		// Current value
 
 
+  if (!a)
+    return;
+
   putc('[', fp);
   for (i = a->num_values, v = a->values; i > 0; i --, v ++)
     _pdfioValueDebug(v, fp);

pdfio-dict.c

@@ -194,6 +194,9 @@ _pdfioDictDebug(pdfio_dict_t *dict,	// I - Dictionary
   _pdfio_pair_t	*pair;			// Current pair
 
 
+  if (!dict)
+    return;
+
   for (i = dict->num_pairs, pair = dict->pairs; i > 0; i --, pair ++)
   {
     fprintf(fp, "/%s", pair->key);

pdfio-file.c

@@ -188,6 +188,8 @@ pdfioFileCreate(
   int		fd;			// File descriptor
 
 
+  PDFIO_DEBUG("pdfioFileCreate(filename=\"%s\", version=\"%s\", media_box=%p, crop_box=%p, error_cb=%p, error_cbdata=%p)\n", filename, version, (void *)media_box, (void *)crop_box, (void *)error_cb, (void *)error_cbdata);
+
   // Range check input...
   if (!filename)
     return (NULL);
@@ -390,6 +392,8 @@ pdfioFileCreateOutput(
     pdfio_error_cb_t  error_cb,		// I - Error callback or `NULL` for default
     void              *error_cbdata)	// I - Error callback data, if any
 {
+  PDFIO_DEBUG("pdfioFileCreate(output_cb=%p, output_cbdata=%p, version=\"%s\", media_box=%p, crop_box=%p, error_cb=%p, error_cbdata=%p)\n", (void *)output_cb, (void *)output_cbdata, version, (void *)media_box, (void *)crop_box, (void *)error_cb, (void *)error_cbdata);
+
   return (create_common("output.pdf", /*fd*/-1, output_cb, output_cbdata, version, media_box, crop_box, error_cb, error_cbdata));
 }
 
@@ -524,6 +528,8 @@ pdfioFileCreateTemporary(
   unsigned	tmpnum;			// Temporary filename number
 
 
+  PDFIO_DEBUG("pdfioFileCreate(buffer=%p, bufsize=%lu, version=\"%s\", media_box=%p, crop_box=%p, error_cb=%p, error_cbdata=%p)\n", (void *)buffer, (unsigned long)bufsize, version, (void *)media_box, (void *)crop_box, (void *)error_cb, (void *)error_cbdata);
+
   // Range check input...
   if (!buffer || bufsize < 32)
   {
@@ -648,11 +654,12 @@ pdfioFileFindObj(
   if ((current = number - 1) >= pdf->num_objs)
     current = pdf->num_objs / 2;
 
-  PDFIO_DEBUG("pdfioFileFindObj: objs[current=%lu]=%p\n", (unsigned long)current, (void *)pdf->objs[current]);
+  PDFIO_DEBUG("pdfioFileFindObj: objs[current=%lu]=%p(%lu)\n", (unsigned long)current, (void *)pdf->objs[current], (unsigned long)(pdf->objs[current] ? pdf->objs[current]->number : 0));
 
   if (number == pdf->objs[current]->number)
   {
     // Fast match...
+    PDFIO_DEBUG("pdfioFileFindObj: Returning %lu (%p)\n", (unsigned long)current, pdf->objs[current]);
     return (pdf->objs[current]);
   }
   else if (number < pdf->objs[current]->number)
@@ -679,11 +686,20 @@ pdfioFileFindObj(
   }
 
   if (number == pdf->objs[left]->number)
+  {
+    PDFIO_DEBUG("pdfioFileFindObj: Returning %lu (%p)\n", (unsigned long)left, pdf->objs[left]);
     return (pdf->objs[left]);
+  }
   else if (number == pdf->objs[right]->number)
+  {
+    PDFIO_DEBUG("pdfioFileFindObj: Returning %lu (%p)\n", (unsigned long)right, pdf->objs[right]);
     return (pdf->objs[right]);
+  }
   else
+  {
+    PDFIO_DEBUG("pdfioFileFindObj: Returning NULL\n");
     return (NULL);
+  }
 }
 
 
@@ -928,6 +944,8 @@ pdfioFileOpen(
   off_t		xref_offset;		// Offset to xref table
 
 
+  PDFIO_DEBUG("pdfioFileOpen(filename=\"%s\", password_cb=%p, password_cbdata=%p, error_cb=%p, error_cbdata=%p)\n", filename, (void *)password_cb, (void *)password_cbdata, (void *)error_cb, (void *)error_cbdata);
+
   // Range check input...
   if (!filename)
     return (NULL);
@@ -1285,6 +1303,8 @@ create_common(
   unsigned char	id_value[16];		// File ID value
 
 
+  PDFIO_DEBUG("create_common(filename=\"%s\", fd=%d, output_cb=%p, output_cbdata=%p, version=\"%s\", media_box=%p, crop_box=%p, error_cb=%p, error_cbdata=%p)\n", filename, fd, (void *)output_cb, (void *)output_cbdata, version, (void *)media_box, (void *)crop_box, (void *)error_cb, (void *)error_cbdata);
+
   // Range check input...
   if (!filename || (fd < 0 && !output_cb))
     return (NULL);

pdfio-object.c

@@ -1,7 +1,7 @@
 //
 // PDF object functions for PDFio.
 //
-// Copyright © 2021-2023 by Michael R Sweet.
+// Copyright © 2021-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -347,8 +347,21 @@ pdfioObjGetNumber(pdfio_obj_t *obj)	// I - Object
 //
 // 'pdfioObjGetSubtype()' - Get an object's subtype.
 //
+// This function returns an object's PDF subtype name, if any.  Common subtype
+// names include:
+//
+// - "CIDFontType0": A CID Type0 font
+// - "CIDFontType2": A CID TrueType font
+// - "Image": An image or image mask
+// - "Form": A fillable form
+// - "OpenType": An OpenType font
+// - "Type0": A composite font
+// - "Type1": A PostScript Type1 font
+// - "Type3": A PDF Type3 font
+// - "TrueType": A TrueType font
+//
 
-const char *				// O - Object subtype
+const char *				// O - Object subtype name or `NULL` for none
 pdfioObjGetSubtype(pdfio_obj_t *obj)	// I - Object
 {
   pdfio_dict_t	*dict;			// Object dictionary
@@ -364,8 +377,21 @@ pdfioObjGetSubtype(pdfio_obj_t *obj)	// I - Object
 //
 // 'pdfioObjGetType()' - Get an object's type.
 //
+// This function returns an object's PDF type name, if any. Common type names
+// include:
+//
+// - "CMap": A character map for composite fonts
+// - "Font": An embedded font (@link pdfioObjGetSubtype@ will tell you the
+//   font format)
+// - "FontDescriptor": A font descriptor
+// - "Page": A (visible) page
+// - "Pages": A page tree node
+// - "Template": An invisible template page
+// - "XObject": An image, image mask, or form (@link pdfioObjGetSubtype@ will
+//   tell you which)
+//
 
-const char *				// O - Object type
+const char *				// O - Object type name or `NULL` for none
 pdfioObjGetType(pdfio_obj_t *obj)	// I - Object
 {
   pdfio_dict_t	*dict;			// Object dictionary

pdfio-stream.c

@@ -408,6 +408,7 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
   pdfio_stream_t	*st;		// Stream
   pdfio_dict_t		*dict = pdfioObjGetDict(obj);
 					// Object dictionary
+  const char		*type;		// Object type
 
 
   PDFIO_DEBUG("_pdfioStreamOpen(obj=%p(%u), decode=%s)\n", obj, (unsigned)obj->number, decode ? "true" : "false");
@@ -434,7 +435,9 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
     return (NULL);
   }
 
-  if (obj->pdf->encryption)
+  type = pdfioObjGetType(obj);
+
+  if (obj->pdf->encryption && (!type || strcmp(type, "XRef")))
   {
     uint8_t	iv[64];			// Initialization vector
     size_t	ivlen;			// Length of initialization vector, if any
@@ -1061,19 +1064,11 @@ stream_read(pdfio_stream_t *st,		// I - Stream
       st->flate.next_out  = (Bytef *)buffer;
       st->flate.avail_out = (uInt)bytes;
 
-      avail_in  = st->flate.avail_in;
-      avail_out = st->flate.avail_out;
-
       if ((status = inflate(&(st->flate), Z_NO_FLUSH)) < Z_OK)
       {
 	_pdfioFileError(st->pdf, "Unable to decompress stream data for object %ld: %s", (long)st->obj->number, zstrerror(status));
 	return (-1);
       }
-      else if (avail_in == st->flate.avail_in && avail_out == st->flate.avail_out)
-      {
-	_pdfioFileError(st->pdf, "Corrupt stream data.");
-	return (-1);
-      }
 
       return (st->flate.next_out - (Bytef *)buffer);
     }

pdfio-value.c

@@ -215,6 +215,9 @@ void
 _pdfioValueDebug(_pdfio_value_t *v,	// I - Value
 		 FILE           *fp)	// I - Output file
 {
+  if (!v)
+    return;
+
   switch (v->type)
   {
     case PDFIO_VALTYPE_ARRAY :

pdfio.h

@@ -23,7 +23,7 @@ extern "C" {
 // Version number...
 //
 
-#  define PDFIO_VERSION		"1.3.1"
+#  define PDFIO_VERSION		"1.3.2"
 
 
 //

pdfio1.def

@@ -1,7 +1,8 @@
 LIBRARY pdfio1
-VERSION 1.2
+VERSION 1.3
 EXPORTS
 _pdfioArrayDebug
+_pdfioArrayDecrypt
 _pdfioArrayDelete
 _pdfioArrayGetValue
 _pdfioArrayRead
@@ -24,6 +25,7 @@ _pdfioCryptoSHA256Init
 _pdfioCryptoUnlock
 _pdfioDictClear
 _pdfioDictDebug
+_pdfioDictDecrypt
 _pdfioDictDelete
 _pdfioDictGetValue
 _pdfioDictRead
@@ -61,9 +63,12 @@ _pdfioTokenPush
 _pdfioTokenRead
 _pdfioValueCopy
 _pdfioValueDebug
+_pdfioValueDecrypt
 _pdfioValueDelete
 _pdfioValueRead
 _pdfioValueWrite
+_pdfio_strtod
+_pdfio_vsnprintf
 pdfioArrayAppendArray
 pdfioArrayAppendBinary
 pdfioArrayAppendBoolean
@@ -190,6 +195,7 @@ pdfioFileCreateStringObj
 pdfioFileCreateTemporary
 pdfioFileFindObj
 pdfioFileGetAuthor
+pdfioFileGetCatalog
 pdfioFileGetCreationDate
 pdfioFileGetCreator
 pdfioFileGetID

pdfio_native.nuspec

@@ -3,7 +3,7 @@
     <metadata>
         <id>pdfio_native</id>
         <title>PDFio Library for VS2019+</title>
-        <version>1.3.1</version>
+        <version>1.3.2</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="1.3.1" />
+	    <dependency id="pdfio_native.redist" version="1.3.2" />
 	    <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>1.3.1</version>
+        <version>1.3.2</version>
         <authors>Michael R Sweet</authors>
         <owners>michaelrsweet</owners>
         <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>

testpdfio.c

@@ -27,7 +27,7 @@
 //
 
 static int	do_crypto_tests(void);
-static int	do_test_file(const char *filename, int objnum, bool verbose);
+static int	do_test_file(const char *filename, int objnum, const char *password, bool verbose);
 static int	do_unit_tests(void);
 static int	draw_image(pdfio_stream_t *st, const char *name, double x, double y, double w, double h, const char *label);
 static bool	error_cb(pdfio_file_t *pdf, const char *message, bool *error);
@@ -37,6 +37,7 @@ static const char *password_cb(void *data, const char *filename);
 static int	read_unit_file(const char *filename, size_t num_pages, size_t first_image, bool is_output);
 static ssize_t	token_consume_cb(const char **s, size_t bytes);
 static ssize_t	token_peek_cb(const char **s, char *buffer, size_t bytes);
+static int	usage(FILE *fp);
 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);
@@ -62,19 +63,30 @@ main(int  argc,				// I - Number of command-line arguments
   int		ret = 0;		// Return value
 
 
-  fprintf(stderr, "testpdfio: Test locale is \"%s\".\n", setlocale(LC_ALL, getenv("LANG")));
-
   if (argc > 1)
   {
     int		i;			// Looping var
+    const char	*password = NULL;	// Password
     bool	verbose = false;	// Be verbose?
 
     for (i = 1; i < argc; i ++)
     {
       if (!strcmp(argv[i], "--help"))
       {
-        puts("Usage: ./testpdfio [--help] [--verbose] [filename [objnum] ...]");
+        return (usage(stdout));
-        return (0);
+      }
+      else if (!strcmp(argv[i], "--password"))
+      {
+        i ++;
+        if (i < argc)
+        {
+          password = argv[i];
+        }
+        else
+        {
+          fputs("testpdfio: Missing password after '--password'.\n", stderr);
+          return (usage(stderr));
+        }
       }
       else if (!strcmp(argv[i], "--verbose"))
       {
@@ -82,24 +94,27 @@ main(int  argc,				// I - Number of command-line arguments
       }
       else if (argv[i][0] == '-')
       {
-        printf("Unknown option '%s'.\n\n", argv[i]);
+        fprintf(stderr, "testpdfio: Unknown option '%s'.\n", argv[i]);
-        puts("Usage: ./testpdfio [--help] [--verbose] [filename [objnum] ...]");
+        return (usage(stderr));
-        return (1);
       }
       else if ((i + 1) < argc && isdigit(argv[i + 1][0] & 255))
       {
         // filename.pdf object-number
-        if (do_test_file(argv[i], atoi(argv[i + 1]), verbose))
+        if (do_test_file(argv[i], atoi(argv[i + 1]), password, verbose))
 	  ret = 1;
 
 	i ++;
       }
-      else if (do_test_file(argv[i], 0, verbose))
+      else if (do_test_file(argv[i], 0, password, verbose))
+      {
         ret = 1;
       }
     }
+  }
   else
   {
+    fprintf(stderr, "testpdfio: Test locale is \"%s\".\n", setlocale(LC_ALL, getenv("LANG")));
+
 #if _WIN32
     // Windows puts executables in Platform/Configuration subdirs...
     if (!_access("../../testfiles", 0))
@@ -363,6 +378,7 @@ do_crypto_tests(void)
 static int				// O - Exit status
 do_test_file(const char *filename,	// I - PDF filename
              int        objnum,		// I - Object number to dump, if any
+             const char *password,	// I - Password for file
              bool       verbose)	// I - Be verbose?
 {
   bool		error = false;		// Have we shown an error yet?
@@ -381,7 +397,7 @@ do_test_file(const char *filename,	// I - PDF filename
     fflush(stdout);
   }
 
-  if ((pdf = pdfioFileOpen(filename, /*password_cb*/NULL, /*password_data*/NULL, (pdfio_error_cb_t)error_cb, &error)) != NULL)
+  if ((pdf = pdfioFileOpen(filename, password_cb, (void *)password, (pdfio_error_cb_t)error_cb, &error)) != NULL)
   {
     if (objnum)
     {
@@ -1559,6 +1575,23 @@ token_peek_cb(const char **s,		// IO - Test string
 }
 
 
+//
+// 'usage()' - Show program usage.
+//
+
+static int				// O - Exit status
+usage(FILE *fp)				// I - Output file
+{
+  fputs("Usage: ./testpdfio [OPTIONS] [FILENAME [OBJNUM]] ...\n", fp);
+  fputs("Options:\n", fp);
+  fputs("  --help               Show program help.\n", fp);
+  fputs("  --password PASSWORD  Set PDF password.\n", fp);
+  fputs("  --verbose            Be verbose.\n", fp);
+
+  return (fp != stdout);
+}
+
+
 //
 // 'verify_image()' - Verify an image object.
 //

testttf.c

@@ -3,7 +3,7 @@
 //
 //     https://github.com/michaelrsweet/ttf
 //
-// Copyright © 2018-2023 by Michael R Sweet.
+// Copyright © 2018-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -120,6 +120,7 @@ test_font(const char *filename)		// I - Font filename
 
 
   printf("ttfCreate(\"%s\"): ", filename);
+  fflush(stdout);
   if ((font = ttfCreate(filename, 0, error_cb, NULL)) != NULL)
     puts("PASS");
   else

ttf.c

@@ -62,7 +62,7 @@
 #  define O_CREAT	_O_CREAT
 #  define O_TRUNC	_O_TRUNC
 
-typedef __int64 ssize_t;		// POSIX type not present on Windows...
+typedef __int64 ssize_t;		// POSIX type not present on Windows... @private@
 
 #else
 #  include <unistd.h>
@@ -100,6 +100,8 @@ typedef __int64 ssize_t;		// POSIX type not present on Windows...
 
 #define TTF_FONT_MAX_CHAR	262144	// Maximum number of character values
 #define TTF_FONT_MAX_GROUPS	65536	// Maximum number of sub-groups
+#define TTF_FONT_MAX_NAMES	16777216// Maximum size of names table we support
+
 
 //
 // TTF/OFF tag constants...
@@ -254,7 +256,7 @@ typedef struct _ttf_off_hhea_s		// Horizontal header
 {
   short		ascender,		// Ascender
 		descender;		// Descender
-  int		numberOfHMetrics;	// Number of horizontal metrics
+  unsigned short numberOfHMetrics;	// Number of horizontal metrics
 } _ttf_off_hhea_t;
 
 typedef struct _ttf_off_os_2_s		// OS/2 information
@@ -297,7 +299,28 @@ static unsigned	seek_table(ttf_t *font, unsigned tag, unsigned offset, bool requ
 
 
 //
-// 'ttfCreate()' - Create a new font object for the named font family.
+// 'ttfCreate()' - Create a new font object for the named font file.
+//
+// This function creates a new font object for the named TrueType or OpenType
+// font file or collection.  The "filename" argument specifies the name of the
+// file to read.
+//
+// The "idx" argument specifies the font to load from a collection - the first
+// font is number `0`.  Once created, you can call the @link ttfGetNumFonts@
+// function to determine whether the loaded font file is a collection with more
+// than one font.
+//
+// The "err_cb" and "err_data" arguments specify a callback function and data
+// pointer for receiving error messages.  If `NULL`, errors are sent to the
+// `stderr` file.  The callback function receives the data pointer and a text
+// message string, for example:
+//
+// ```
+// void my_err_cb(void *err_data, const char *message)
+// {
+//   fprintf(stderr, "ERROR: %s\n", message);
+// }
+// ```
 //
 
 ttf_t *					// O - New font object
@@ -550,6 +573,10 @@ ttfGetAscent(ttf_t *font)		// I - Font
 //
 // 'ttfGetBounds()' - Get the bounds of all characters in a font.
 //
+// This function gets the bounds of all characters in a font.  The "bounds"
+// argument is a pointer to a `ttf_rect_t` structure that will be filled with
+// the limits for characters in the font scaled to a 1000x1000 unit square.
+//
 
 ttf_rect_t *				// O - Bounds or `NULL` on error
 ttfGetBounds(ttf_t      *font,		// I - Font
@@ -631,8 +658,11 @@ ttfGetDescent(ttf_t *font)		// I - Font
 //
 // 'ttfGetExtents()' - Get the extents of a UTF-8 string.
 //
-// This function computes the extents of a UTF-8 string when rendered using the
+// This function computes the extents of the UTF-8 string "s" when rendered
-// specified font and size.
+// using the specified font "font" and size "size".  The "extents" argument is
+// a pointer to a `ttf_rect_t` structure that is filled with the extents of a
+// simple rendering of the string with no kerning or rewriting applied.  The
+// values are scaled using the specified font size.
 //
 
 ttf_rect_t *				// O - Pointer to extents or `NULL` on error
@@ -1272,23 +1302,34 @@ read_cmap(ttf_t *font)			// I - Font
           for (i = 0; i < numGlyphIdArray; i ++)
             glyphIdArray[i] = read_ushort(font);
 
-#ifdef DEBUG
+          for (i = 0, segment = segments; i < segCount; i ++, segment ++)
-          for (i = 0; i < segCount; i ++)
+          {
-            TTF_DEBUG("read_cmap: segment[%d].startCode=%d, endCode=%d, idDelta=%d, idRangeOffset=%d\n", i, segments[i].startCode, segments[i].endCode, segments[i].idDelta, segments[i].idRangeOffset);
+            TTF_DEBUG("read_cmap: segment[%d].startCode=%d, endCode=%d, idDelta=%d, idRangeOffset=%d\n", i, segment->startCode, segment->endCode, segment->idDelta, segment->idRangeOffset);
 
+            if (segment->startCode > segment->endCode)
+            {
+	      errorf(font, "Bad cmap table segment %u to %u.", segments->startCode, segment->endCode);
+	      free(segments);
+	      free(glyphIdArray);
+	      return (false);
+            }
+
+            // Based on the end code of the segment table, allocate space for the
+            // uncompressed cmap table...
+            if (segment->endCode >= font->num_cmap)
+	      font->num_cmap = segment->endCode + 1;
+          }
+
+#ifdef DEBUG
           for (i = 0; i < numGlyphIdArray; i ++)
             TTF_DEBUG("read_cmap: glyphIdArray[%d]=%d\n", i, glyphIdArray[i]);
 #endif /* DEBUG */
 
-          // Based on the end code of the segent table, allocate space for the
+	  if (font->num_cmap == 0 || font->num_cmap > TTF_FONT_MAX_CHAR)
-          // uncompressed cmap table...
-//          segCount --;			// Last segment is not used (sigh)
-
-	  font->num_cmap = segments[segCount - 1].endCode + 1;
-
-	  if (font->num_cmap > TTF_FONT_MAX_CHAR)
 	  {
 	    errorf(font, "Invalid cmap table with %u characters.", (unsigned)font->num_cmap);
+	    free(segments);
+	    free(glyphIdArray);
 	    return (false);
 	  }
 
@@ -1382,6 +1423,13 @@ read_cmap(ttf_t *font)			// I - Font
 	    group->startGlyphID  = read_ulong(font);
 	    TTF_DEBUG("read_cmap: [%u] startCharCode=%u, endCharCode=%u, startGlyphID=%u\n", gidx, group->startCharCode, group->endCharCode, group->startGlyphID);
 
+            if (group->startCharCode > group->endCharCode)
+            {
+	      errorf(font, "Bad cmap table segment %u to %u.", group->startCharCode, group->endCharCode);
+	      free(groups);
+	      return (false);
+            }
+
             if (group->endCharCode >= font->num_cmap)
               font->num_cmap = group->endCharCode + 1;
 	  }
@@ -1390,9 +1438,10 @@ read_cmap(ttf_t *font)			// I - Font
 	  // uncompressed cmap table...
           TTF_DEBUG("read_cmap: num_cmap=%u\n", (unsigned)font->num_cmap);
 
-	  if (font->num_cmap > TTF_FONT_MAX_CHAR)
+	  if (font->num_cmap == 0 || font->num_cmap > TTF_FONT_MAX_CHAR)
 	  {
 	    errorf(font, "Invalid cmap table with %u characters.", (unsigned)font->num_cmap);
+	    free(groups);
 	    return (false);
 	  }
 
@@ -1465,6 +1514,13 @@ read_cmap(ttf_t *font)			// I - Font
 	    group->glyphID       = read_ulong(font);
 	    TTF_DEBUG("read_cmap: [%u] startCharCode=%u, endCharCode=%u, glyphID=%u\n", gidx, group->startCharCode, group->endCharCode, group->glyphID);
 
+            if (group->startCharCode > group->endCharCode)
+            {
+	      errorf(font, "Bad cmap table segment %u to %u.", group->startCharCode, group->endCharCode);
+	      free(groups);
+	      return (false);
+            }
+
             if (group->endCharCode >= font->num_cmap)
               font->num_cmap = group->endCharCode + 1;
 	  }
@@ -1473,9 +1529,10 @@ read_cmap(ttf_t *font)			// I - Font
 	  // uncompressed cmap table...
           TTF_DEBUG("read_cmap: num_cmap=%u\n", (unsigned)font->num_cmap);
 
-	  if (font->num_cmap > TTF_FONT_MAX_CHAR)
+	  if (font->num_cmap == 0 || font->num_cmap > TTF_FONT_MAX_CHAR)
 	  {
 	    errorf(font, "Invalid cmap table with %u characters.", (unsigned)font->num_cmap);
+	    free(groups);
 	    return (false);
 	  }
 
@@ -1598,7 +1655,7 @@ read_hmtx(ttf_t           *font,	// I - Font
           _ttf_off_hhea_t *hhea)	// O - hhea table data
 {
   unsigned	length;			// Length of hmtx table
-  int		i;			// Looping var
+  unsigned	i;			// Looping var
   _ttf_metric_t	*widths;		// Glyph metrics array
 
 
@@ -1677,8 +1734,15 @@ read_names(ttf_t *font)			// I - Font
     return (false);
 
   font->names.storage_size = length - (unsigned)offset;
+  if (font->names.storage_size > TTF_FONT_MAX_NAMES)
+  {
+    errorf(font, "Name table too large - %u bytes.", (unsigned)font->names.storage_size);
+    return (false);
+  }
+
   if ((font->names.storage = malloc(font->names.storage_size)) == NULL)
     return (false);
+
   memset(font->names.storage, 'A', font->names.storage_size);
 
   for (i = font->names.num_names, name = font->names.names; i > 0; i --, name ++)

ttf.h

@@ -3,7 +3,7 @@
 //
 //     https://github.com/michaelrsweet/ttf
 //
-// Copyright © 2018-2023 by Michael R Sweet.
+// Copyright © 2018-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -22,12 +22,12 @@ extern "C" {
 // Types...
 //
 
-typedef struct _ttf_s ttf_t;	//// Font object
+typedef struct _ttf_s ttf_t;	// Font object
 
 typedef void (*ttf_err_cb_t)(void *data, const char *message);
-				//// Font error callback
+				// Font error callback
 
-typedef enum ttf_stretch_e	//// Font stretch
+typedef enum ttf_stretch_e	// Font stretch
 {
   TTF_STRETCH_NORMAL,		// normal
   TTF_STRETCH_ULTRA_CONDENSED,	// ultra-condensed
@@ -40,20 +40,20 @@ typedef enum ttf_stretch_e	//// Font stretch
   TTF_STRETCH_ULTRA_EXPANDED	// ultra-expanded
 } ttf_stretch_t;
 
-typedef enum ttf_style_e	//// Font style
+typedef enum ttf_style_e	// Font style
 {
   TTF_STYLE_NORMAL,		// Normal font
   TTF_STYLE_ITALIC,		// Italic font
   TTF_STYLE_OBLIQUE		// Oblique (angled) font
 } ttf_style_t;
 
-typedef enum ttf_variant_e	//// Font variant
+typedef enum ttf_variant_e	// Font variant
 {
   TTF_VARIANT_NORMAL,		// Normal font
   TTF_VARIANT_SMALL_CAPS	// Font whose lowercase letters are small capitals
 } ttf_variant_t;
 
-typedef enum ttf_weight_e	//// Font weight
+typedef enum ttf_weight_e	// Font weight
 {
   TTF_WEIGHT_100 = 100,		// Weight 100 (Thin)
   TTF_WEIGHT_200 = 200,		// Weight 200 (Extra/Ultra-Light)
@@ -66,7 +66,7 @@ typedef enum ttf_weight_e	//// Font weight
   TTF_WEIGHT_900 = 900		// Weight 900 (Black/Heavy)
 } ttf_weight_t;
 
-typedef struct ttf_rect_s	//// Bounding rectangle
+typedef struct ttf_rect_s	// Bounding rectangle
 {
   float	left;			// Left offset
   float	top;			// Top offset