dany/pdfio
1
0
Fork 0
mirror of https://github.com/michaelrsweet/pdfio.git synced 2026-01-18 01:30:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

Implement pdfioPageGetXxx functions (Issue #150)

Browse Source
This commit is contained in:
Michael R Sweet
2026-01-16 20:54:02 -05:00
parent 3c60d4a886
commit 4e9ec397f1
7 changed files with 678 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGES.md
View File

@@ -9,6 +9,8 @@ v1.7.0 - YYYY-MM-DD
- Added support for basic compound stream filters for ASCII85Decode support
(Issue #11)
- Added support for LZWDecode filters (Issue #11)
- Added `pdfioPageGetXxx` functions to get values from the page dictionaries
(Issue #150)
- Fixed a buffer overflow in the (still not enabled) AES-256 code.

148
doc/pdfio.3
View File

@@ -1,4 +1,4 @@
.TH pdfio 3 "pdf read/write library" "2025-10-05" "pdf read/write library"
.TH pdfio 3 "pdf read/write library" "2026-01-16" "pdf read/write library"
.SH NAME
pdfio \- pdf read/write library
.SH Introduction
@@ -2555,7 +2555,7 @@ ASCIIHexDecode filter (reading only)
.TP 5
PDFIO_FILTER_CCITTFAX
.br
CCITTFaxDecode filter
CCITTFaxDecode filter (reading only)
.TP 5
PDFIO_FILTER_CRYPT
.br
@@ -2571,7 +2571,7 @@ FlateDecode filter
.TP 5
PDFIO_FILTER_JBIG2
.br
JBIG2Decode filter
JBIG2Decode filter (reading only)
.TP 5
PDFIO_FILTER_JPX
.br
@@ -4924,6 +4924,91 @@ bool pdfioPageDictAddImage (
pdfio_obj_t *obj
);
.fi
.SS pdfioPageGetArray
Get an array value from the page dictionary.
.PP
.nf
pdfio_array_t * pdfioPageGetArray (
pdfio_obj_t *page,
const char *key
);
.fi
.PP
This function looks up an array value in the page dictionary, either in the
specified object or one of its parents.
.SS pdfioPageGetBinary
Get a binary value from the page dictionary.
.PP
.nf
unsigned char * pdfioPageGetBinary (
pdfio_obj_t *page,
const char *key,
size_t *length
);
.fi
.PP
This function looks up a binary value in the page dictionary, either in the
specified object or one of its parents.
.SS pdfioPageGetBoolean
Get a boolean value from the page dictionary.
.PP
.nf
bool pdfioPageGetBoolean (
pdfio_obj_t *page,
const char *key
);
.fi
.PP
This function looks up a boolean value in the page dictionary, either in the
specified object or one of its parents.
.SS pdfioPageGetDate
Get a date value from the page dictionary.
.PP
.nf
time_t pdfioPageGetDate (
pdfio_obj_t *page,
const char *key
);
.fi
.PP
This function looks up a date value in the page dictionary, either in the
specified object or one of its parents.
.SS pdfioPageGetDict
Get a dictionary value from the page dictionary.
.PP
.nf
pdfio_dict_t * pdfioPageGetDict (
pdfio_obj_t *page,
const char *key
);
.fi
.PP
This function looks up a dictionary value in the page dictionary, either in
the specified object or one of its parents.
.SS pdfioPageGetName
Get a name value from the page dictionary.
.PP
.nf
const char * pdfioPageGetName (
pdfio_obj_t *page,
const char *key
);
.fi
.PP
This function looks up a name value in the page dictionary, either in the
specified object or one of its parents.
.SS pdfioPageGetNumStreams
Get the number of content streams for a page object.
.PP
@@ -4932,6 +5017,63 @@ size_t pdfioPageGetNumStreams (
pdfio_obj_t *page
);
.fi
.SS pdfioPageGetNumber
Get a number value from the page dictionary.
.PP
.nf
double pdfioPageGetNumber (
pdfio_obj_t *page,
const char *key
);
.fi
.PP
This function looks up a number value in the page dictionary, either in the
specified object or one of its parents.
.SS pdfioPageGetObj
Get an indirect object value from the page dictionary.
.PP
.nf
pdfio_obj_t * pdfioPageGetObj (
pdfio_obj_t *page,
const char *key
);
.fi
.PP
This function looks up an indirect object value in the page dictionary,
either in the specified object or one of its parents.
.SS pdfioPageGetRect
Get a rectangle value from the page dictionary.
.PP
.nf
pdfio_rect_t * pdfioPageGetRect (
pdfio_obj_t *page,
const char *key,
pdfio_rect_t *rect
);
.fi
.PP
This function looks up a rectangle value in the page dictionary, either in
the specified object or one of its parents.
.SS pdfioPageGetString
Get a string value from the page dictionary.
.PP
.nf
const char * pdfioPageGetString (
pdfio_obj_t *page,
const char *key
);
.fi
.PP
This function looks up a string value in the page dictionary, either in the
specified object or one of its parents.
.SS pdfioPageOpenStream
Open a content stream for a page.
.PP

226
doc/pdfio.html
View File

@@ -1,13 +1,13 @@
<!DOCTYPE html>
<html lang="en-US">
<head>
<title>PDFio Programming Manual v1.6.0</title>
<title>PDFio Programming Manual v1.7.0</title>
<meta http-equiv="Content-Type" content="text/html;charset=utf-8">
<meta name="generator" content="codedoc v3.8">
<meta name="author" content="Michael R Sweet">
<meta name="language" content="en-US">
<meta name="copyright" content="Copyright © 2021-2025 by Michael R Sweet">
<meta name="version" content="1.6.0">
<meta name="version" content="1.7.0">
<style type="text/css"><!--
body {
background: white;
@@ -92,13 +92,16 @@ blockquote :first-child {
margin-bottom: 0;
}
p code, li code, p.code, pre, ul.code li {
background: rgba(127,127,127,0.25);
border: thin dotted gray;
font-family: monospace;
hyphens: manual;
-webkit-hyphens: manual;
}
p code, li code {
padding: 0 5px;
}
p.code, pre, ul.code li {
background: rgba(127,127,127,0.25);
border: thin dotted gray;
padding: 10px;
page-break-inside: avoid;
}
@@ -217,6 +220,21 @@ span.string {
a:link:hover, a:visited:hover, a:active {
color: #f06;
}
span.comment {
color: #7c7;
}
span.directive {
color: red;
}
span.number {
color: #c64;
}
span.reserved {
color: #77f;
}
span.string {
color: #f7f;
}
}
/* Show contents on left side in web browser */
@media screen and (min-width: 800px) {
@@ -251,7 +269,7 @@ span.string {
<body>
<div class="header">
<p><img class="title" src="pdfio-512.png"></p>
<h1 class="title">PDFio Programming Manual v1.6.0</h1>
<h1 class="title">PDFio Programming Manual v1.7.0</h1>
<p>Michael R Sweet</p>
<p>Copyright © 2021-2025 by Michael R Sweet</p>
</div>
@@ -464,7 +482,17 @@ span.string {
<li><a href="#pdfioPageDictAddColorSpace">pdfioPageDictAddColorSpace</a></li>
<li><a href="#pdfioPageDictAddFont">pdfioPageDictAddFont</a></li>
<li><a href="#pdfioPageDictAddImage">pdfioPageDictAddImage</a></li>
<li><a href="#pdfioPageGetArray">pdfioPageGetArray</a></li>
<li><a href="#pdfioPageGetBinary">pdfioPageGetBinary</a></li>
<li><a href="#pdfioPageGetBoolean">pdfioPageGetBoolean</a></li>
<li><a href="#pdfioPageGetDate">pdfioPageGetDate</a></li>
<li><a href="#pdfioPageGetDict">pdfioPageGetDict</a></li>
<li><a href="#pdfioPageGetName">pdfioPageGetName</a></li>
<li><a href="#pdfioPageGetNumStreams">pdfioPageGetNumStreams</a></li>
<li><a href="#pdfioPageGetNumber">pdfioPageGetNumber</a></li>
<li><a href="#pdfioPageGetObj">pdfioPageGetObj</a></li>
<li><a href="#pdfioPageGetRect">pdfioPageGetRect</a></li>
<li><a href="#pdfioPageGetString">pdfioPageGetString</a></li>
<li><a href="#pdfioPageOpenStream">pdfioPageOpenStream</a></li>
<li><a href="#pdfioStreamClose">pdfioStreamClose</a></li>
<li><a href="#pdfioStreamConsume">pdfioStreamConsume</a></li>
@@ -5409,6 +5437,116 @@ array that was created using the
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description"><code>true</code> on success, <code>false</code> on failure</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetArray">pdfioPageGetArray</a></h3>
<p class="description">Get an array value from the page dictionary.</p>
<p class="code">
<a href="#pdfio_array_t">pdfio_array_t</a> *pdfioPageGetArray(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Array or <code>NULL</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up an array value in the page dictionary, either in the
specified object or one of its parents.
</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetBinary">pdfioPageGetBinary</a></h3>
<p class="description">Get a binary value from the page dictionary.</p>
<p class="code">
<span class="reserved">unsigned</span> <span class="reserved">char</span> *pdfioPageGetBinary(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key, size_t *length);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
<tr><th>length</th>
<td class="description">Length of value</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Pointer to binary data or <code>NULL</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up a binary value in the page dictionary, either in the
specified object or one of its parents.
</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetBoolean">pdfioPageGetBoolean</a></h3>
<p class="description">Get a boolean value from the page dictionary.</p>
<p class="code">
<span class="reserved">bool</span> pdfioPageGetBoolean(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Boolean value or <code>false</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up a boolean value in the page dictionary, either in the
specified object or one of its parents.
</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetDate">pdfioPageGetDate</a></h3>
<p class="description">Get a date value from the page dictionary.</p>
<p class="code">
time_t pdfioPageGetDate(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Date/time or <code>0</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up a date value in the page dictionary, either in the
specified object or one of its parents.
</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetDict">pdfioPageGetDict</a></h3>
<p class="description">Get a dictionary value from the page dictionary.</p>
<p class="code">
<a href="#pdfio_dict_t">pdfio_dict_t</a> *pdfioPageGetDict(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Dictionary or <code>NULL</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up a dictionary value in the page dictionary, either in
the specified object or one of its parents.
</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetName">pdfioPageGetName</a></h3>
<p class="description">Get a name value from the page dictionary.</p>
<p class="code">
<span class="reserved">const</span> <span class="reserved">char</span> *pdfioPageGetName(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Name string or <code>NULL</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up a name value in the page dictionary, either in the
specified object or one of its parents.
</p>
<h3 class="function"><a id="pdfioPageGetNumStreams">pdfioPageGetNumStreams</a></h3>
<p class="description">Get the number of content streams for a page object.</p>
<p class="code">
@@ -5420,6 +5558,80 @@ size_t pdfioPageGetNumStreams(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page);</p>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Number of streams</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetNumber">pdfioPageGetNumber</a></h3>
<p class="description">Get a number value from the page dictionary.</p>
<p class="code">
<span class="reserved">double</span> pdfioPageGetNumber(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Number value or <code>0.0</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up a number value in the page dictionary, either in the
specified object or one of its parents.
</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetObj">pdfioPageGetObj</a></h3>
<p class="description">Get an indirect object value from the page dictionary.</p>
<p class="code">
<a href="#pdfio_obj_t">pdfio_obj_t</a> *pdfioPageGetObj(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Object or <code>NULL</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up an indirect object value in the page dictionary,
either in the specified object or one of its parents.
</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetRect">pdfioPageGetRect</a></h3>
<p class="description">Get a rectangle value from the page dictionary.</p>
<p class="code">
<a href="#pdfio_rect_t">pdfio_rect_t</a> *pdfioPageGetRect(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key, <a href="#pdfio_rect_t">pdfio_rect_t</a> *rect);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
<tr><th>rect</th>
<td class="description">Rectangle</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">Rectangle or <code>NULL</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up a rectangle value in the page dictionary, either in
the specified object or one of its parents.
</p>
<h3 class="function"><span class="info">&#160;PDFio 1.7&#160;</span><a id="pdfioPageGetString">pdfioPageGetString</a></h3>
<p class="description">Get a string value from the page dictionary.</p>
<p class="code">
<span class="reserved">const</span> <span class="reserved">char</span> *pdfioPageGetString(<a href="#pdfio_obj_t">pdfio_obj_t</a> *page, <span class="reserved">const</span> <span class="reserved">char</span> *key);</p>
<h4 class="parameters">Parameters</h4>
<table class="list"><tbody>
<tr><th>page</th>
<td class="description">Page object</td></tr>
<tr><th>key</th>
<td class="description">Dictionary key</td></tr>
</tbody></table>
<h4 class="returnvalue">Return Value</h4>
<p class="description">String value or <code>NULL</code> if none</p>
<h4 class="discussion">Discussion</h4>
<p class="discussion">This function looks up a string value in the page dictionary, either in the
specified object or one of its parents.
</p>
<h3 class="function"><a id="pdfioPageOpenStream">pdfioPageOpenStream</a></h3>
<p class="description">Open a content stream for a page.</p>
<p class="code">
@@ -5759,11 +5971,11 @@ typedef enum <a href="#pdfio_valtype_e">pdfio_valtype_e</a> pdfio_valtype_t;
<table class="list"><tbody>
<tr><th>PDFIO_FILTER_ASCII85 </th><td class="description">ASCII85Decode filter (reading only)</td></tr>
<tr><th>PDFIO_FILTER_ASCIIHEX </th><td class="description">ASCIIHexDecode filter (reading only)</td></tr>
<tr><th>PDFIO_FILTER_CCITTFAX </th><td class="description">CCITTFaxDecode filter</td></tr>
<tr><th>PDFIO_FILTER_CCITTFAX </th><td class="description">CCITTFaxDecode filter (reading only)</td></tr>
<tr><th>PDFIO_FILTER_CRYPT </th><td class="description">Encryption filter</td></tr>
<tr><th>PDFIO_FILTER_DCT </th><td class="description">DCTDecode (JPEG) filter</td></tr>
<tr><th>PDFIO_FILTER_FLATE </th><td class="description">FlateDecode filter</td></tr>
<tr><th>PDFIO_FILTER_JBIG2 </th><td class="description">JBIG2Decode filter</td></tr>
<tr><th>PDFIO_FILTER_JBIG2 </th><td class="description">JBIG2Decode filter (reading only)</td></tr>
<tr><th>PDFIO_FILTER_JPX </th><td class="description">JPXDecode filter (reading only)</td></tr>
<tr><th>PDFIO_FILTER_LZW </th><td class="description">LZWDecode filter (reading only)</td></tr>
<tr><th>PDFIO_FILTER_NONE </th><td class="description">No filter</td></tr>

291
pdfio-page.c
View File

@@ -15,6 +15,7 @@
//
static _pdfio_value_t *get_contents(pdfio_obj_t *page);
static _pdfio_value_t *get_page_value(pdfio_obj_t *page, const char *key);
//
@@ -52,6 +53,158 @@ pdfioPageCopy(pdfio_file_t *pdf, // I - PDF file
}
//
// 'pdfioPageGetArray()' - Get an array value from the page dictionary.
//
// This function looks up an array value in the page dictionary, either in the
// specified object or one of its parents.
//
// @since PDFio 1.7@
//
pdfio_array_t * // O - Array or `NULL` if none
pdfioPageGetArray(pdfio_obj_t *page, // I - Page object
const char *key) // I - Dictionary key
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_ARRAY)
return (v->value.array);
else
return (NULL);
}
//
// 'pdfioPageGetBinary()' - Get a binary value from the page dictionary.
//
// This function looks up a binary value in the page dictionary, either in the
// specified object or one of its parents.
//
// @since PDFio 1.7@
//
unsigned char * // O - Pointer to binary data or `NULL` if none
pdfioPageGetBinary(pdfio_obj_t *page, // I - Page object
const char *key, // I - Dictionary key
size_t *length) // O - Length of value
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_BINARY)
{
if (length)
*length = v->value.binary.datalen;
return (v->value.binary.data);
}
else
{
return (NULL);
}
}
//
// 'pdfioPageGetBoolean()' - Get a boolean value from the page dictionary.
//
// This function looks up a boolean value in the page dictionary, either in the
// specified object or one of its parents.
//
// @since PDFio 1.7@
//
bool // O - Boolean value or `false` if none
pdfioPageGetBoolean(pdfio_obj_t *page, // I - Page object
const char *key) // I - Dictionary key
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_ARRAY)
return (v->value.boolean);
else
return (NULL);
}
//
// 'pdfioPageGetDate()' - Get a date value from the page dictionary.
//
// This function looks up a date value in the page dictionary, either in the
// specified object or one of its parents.
//
// @since PDFio 1.7@
//
time_t // O - Date/time or `0` if none
pdfioPageGetDate(pdfio_obj_t *page, // I - Page object
const char *key) // I - Dictionary key
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_DATE)
return (v->value.date);
else
return (0);
}
//
// 'pdfioPageGetDict()' - Get a dictionary value from the page dictionary.
//
// This function looks up a dictionary value in the page dictionary, either in
// the specified object or one of its parents.
//
// @since PDFio 1.7@
//
pdfio_dict_t * // O - Dictionary or `NULL` if none
pdfioPageGetDict(pdfio_obj_t *page, // I - Page object
const char *key) // I - Dictionary key
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_DICT)
return (v->value.dict);
else
return (NULL);
}
//
// 'pdfioPageGetName()' - Get a name value from the page dictionary.
//
// This function looks up a name value in the page dictionary, either in the
// specified object or one of its parents.
//
// @since PDFio 1.7@
//
const char * // O - Name string or `NULL` if none
pdfioPageGetName(pdfio_obj_t *page, // I - Page object
const char *key) // I - Dictionary key
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_NAME)
return (v->value.name);
else
return (NULL);
}
//
// 'pdfioPageGetNumStreams()' - Get the number of content streams for a page object.
//
@@ -73,6 +226,112 @@ pdfioPageGetNumStreams(
}
//
// 'pdfioPageGetNumber()' - Get a number value from the page dictionary.
//
// This function looks up a number value in the page dictionary, either in the
// specified object or one of its parents.
//
// @since PDFio 1.7@
//
double // O - Number value or `0.0` if none
pdfioPageGetNumber(pdfio_obj_t *page, // I - Page object
const char *key) // I - Dictionary key
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_NUMBER)
return (v->value.number);
else
return (0.0);
}
//
// 'pdfioPageGetObj()' - Get an indirect object value from the page dictionary.
//
// This function looks up an indirect object value in the page dictionary,
// either in the specified object or one of its parents.
//
// @since PDFio 1.7@
//
pdfio_obj_t * // O - Object or `NULL` if none
pdfioPageGetObj(pdfio_obj_t *page, // I - Page object
const char *key) // I - Dictionary key
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_INDIRECT)
return (pdfioFileFindObj(page->pdf, v->value.indirect.number));
else
return (NULL);
}
//
// 'pdfioPageGetRect()' - Get a rectangle value from the page dictionary.
//
// This function looks up a rectangle value in the page dictionary, either in
// the specified object or one of its parents.
//
// @since PDFio 1.7@
//
pdfio_rect_t * // O - Rectangle or `NULL` if none
pdfioPageGetRect(pdfio_obj_t *page, // I - Page object
const char *key, // I - Dictionary key
pdfio_rect_t *rect) // O - Rectangle
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_ARRAY && pdfioArrayGetSize(v->value.array) == 4)
{
rect->x1 = pdfioArrayGetNumber(v->value.array, 0);
rect->y1 = pdfioArrayGetNumber(v->value.array, 1);
rect->x2 = pdfioArrayGetNumber(v->value.array, 2);
rect->y2 = pdfioArrayGetNumber(v->value.array, 3);
return (rect);
}
else
{
return (NULL);
}
}
//
// 'pdfioPageGetString()' - Get a string value from the page dictionary.
//
// This function looks up a string value in the page dictionary, either in the
// specified object or one of its parents.
//
// @since PDFio 1.7@
//
const char * // O - String value or `NULL` if none
pdfioPageGetString(pdfio_obj_t *page, // I - Page object
const char *key) // I - Dictionary key
{
_pdfio_value_t *v = get_page_value(page, key);
// Dictionary value
if (v && v->type == PDFIO_VALTYPE_STRING)
return (v->value.string);
else
return (NULL);
}
//
// 'pdfioPageOpenStream()' - Open a content stream for a page.
//
@@ -158,3 +417,35 @@ get_contents(pdfio_obj_t *page) // I - Page object
return (contents);
}
//
// 'get_page_value()' - Get a page dictionary value, including parents.
//
static _pdfio_value_t * // O - Dictionary value or `NULL` if none
get_page_value(pdfio_obj_t *page, // I - Page object
const char *key) // I - Dictionary key
{
_pdfio_value_t *v = NULL; // Dictionary value
while (page != NULL)
{
// Load the page object as needed...
if (page->value.type == PDFIO_VALTYPE_NONE && !_pdfioObjLoad(page))
break;
// If there isn't a dictionary for the object, stop...
if (page->value.type != PDFIO_VALTYPE_DICT)
break;
// Lookup the key...
if ((v = _pdfioDictGetValue(page->value.value.dict, key)) != NULL)
break;
page = pdfioDictGetObj(page->value.value.dict, "Parent");
}
return (v);
}

10
pdfio.h
View File

@@ -238,7 +238,17 @@ extern const char *pdfioObjGetType(pdfio_obj_t *obj) _PDFIO_PUBLIC;
extern pdfio_stream_t *pdfioObjOpenStream(pdfio_obj_t *obj, bool decode) _PDFIO_PUBLIC;
extern bool pdfioPageCopy(pdfio_file_t *pdf, pdfio_obj_t *srcpage) _PDFIO_PUBLIC;
extern pdfio_array_t *pdfioPageGetArray(pdfio_obj_t *page, const char *key) _PDFIO_PUBLIC;
extern unsigned char *pdfioPageGetBinary(pdfio_obj_t *page, const char *key, size_t *length) _PDFIO_PUBLIC;
extern bool pdfioPageGetBoolean(pdfio_obj_t *page, const char *key) _PDFIO_PUBLIC;
extern time_t pdfioDictPageDate(pdfio_obj_t *page, const char *key) _PDFIO_PUBLIC;
extern pdfio_dict_t *pdfioPageGetDict(pdfio_obj_t *page, const char *key) _PDFIO_PUBLIC;
extern const char *pdfioPageGetName(pdfio_obj_t *page, const char *key) _PDFIO_PUBLIC;
extern size_t pdfioPageGetNumStreams(pdfio_obj_t *page) _PDFIO_PUBLIC;
extern double pdfioPageGetNumber(pdfio_obj_t *page, const char *key) _PDFIO_PUBLIC;
extern pdfio_obj_t *pdfioPageGetObj(pdfio_obj_t *page, const char *key) _PDFIO_PUBLIC;
extern pdfio_rect_t *pdfioPageGetRect(pdfio_obj_t *page, const char *key, pdfio_rect_t *rect) _PDFIO_PUBLIC;
extern const char *pdfioPageGetString(pdfio_obj_t *page, const char *key) _PDFIO_PUBLIC;
extern pdfio_stream_t *pdfioPageOpenStream(pdfio_obj_t *page, size_t n, bool decode) _PDFIO_PUBLIC;
extern bool pdfioStreamClose(pdfio_stream_t *st) _PDFIO_PUBLIC;

10
pdfio1.def
View File

@@ -258,7 +258,17 @@ pdfioPageCopy
pdfioPageDictAddColorSpace
pdfioPageDictAddFont
pdfioPageDictAddImage
pdfioPageGetArray
pdfioPageGetBinary
pdfioPageGetBoolean
pdfioPageGetDate
pdfioPageGetDict
pdfioPageGetName
pdfioPageGetNumber
pdfioPageGetNumStreams
pdfioPageGetObj
pdfioPageGetRect
pdfioPageGetString
pdfioPageOpenStream
pdfioStreamClose
pdfioStreamConsume

14
testpdfio.c
View File

@@ -658,19 +658,7 @@ do_test_file(const char *filename, // I - PDF filename
pdfio_stream_t *st; // Page content stream
memset(&media_box, 0, sizeof(media_box));
dict = pdfioObjGetDict(obj);
if (!pdfioDictGetRect(dict, "MediaBox", &media_box))
{
pdfio_obj_t *parent; // Parent object
while ((parent = pdfioDictGetObj(dict, "Parent")) != NULL)
{
dict = pdfioObjGetDict(parent);
if (pdfioDictGetRect(dict, "MediaBox", &media_box))
break;
}
}
pdfioPageGetRect(obj, "MediaBox", &media_box);
if ((st = pdfioPageOpenStream(obj, /*number*/0, /*decode*/true)) != NULL)
{