Compare commits

...

3 Commits

Author SHA1 Message Date
Michael R Sweet
10c15fc281
Bump NuGet package versions. 2024-12-22 21:33:35 -05:00
Michael R Sweet
fd8427d68a
Add pdf2text example docos, install examples to doc directory. 2024-12-22 21:29:32 -05:00
Michael R Sweet
ed1421287f
Move pdfiototext to examples. 2024-12-22 19:00:17 -05:00
9 changed files with 172 additions and 35 deletions

2
.gitignore vendored
View File

@ -14,6 +14,7 @@
/examples/code128
/examples/image2pdf
/examples/md2pdf
/examples/pdf2text
/examples/pdfioinfo
/Makefile
/packages
@ -21,7 +22,6 @@
/pdfio.xcodeproj/xcshareddata
/pdfio-*.tar.gz*
/pdfio-*.zip*
/pdfiototext
/testpdfio
/testpdfio-*.pdf
/testttf

View File

@ -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 $@...

View File

@ -1081,7 +1081,43 @@ The pdfioinfo.c example program opens a PDF file and prints the title, author, c
return (0);
}
.fi
.SS Create PDF File With Text and Image
.SS Extract Text from PDF File
.PP
The pdf2text.c example code extracts non\-Unicode text from a PDF file by scanning each page for strings and text drawing commands. Since it doesn't look at the font encoding or support Unicode text, it is really only useful to extract plain ASCII text from a PDF file. And since it writes text in the order it appears in the page stream, it may not come out in the same order as appears on the page.
.PP
The pdfioStreamGetToken function is used to read individual tokens from the page streams. Tokens starting with the open parenthesis are text strings, while PDF operators are left as\-is. We use some simple logic to make sure that we include spaces between text strings and add newlines for the text operators that start a new line in a text block:
.nf
pdfio_stream_t *st; // Page stream
bool first = true; // First string on line?
char buffer[1024]; // Token buffer
// Read PDF tokens from the page stream...
while (pdfioStreamGetToken(st, buffer, sizeof(buffer)))
{
if (buffer[0] == '(')
{
// Text string using an 8\-bit encoding
if (first)
first = false;
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;
}
}
if (!first)
putchar('\\n');
.fi
.SS Create a PDF File With Text and an Image
.PP
The image2pdf.c example code creates a PDF file containing a JPEG or PNG image file and optional caption on a single page. The create_pdf_image_file function creates the PDF file, embeds a base font and the named JPEG or PNG image file, and then creates a page with the image centered on the page with any text centered below:
.nf
@ -2038,7 +2074,7 @@ We then loops through the fragments for the current line, drawing checkboxes, im
char targetlink[129]; // Targeted link
targetlink[0] = '#';
make_target_name(targetlink + 1, frag\->text, sizeof(targetlink) \- 1);
make_target_name(targetlink + 1, frag\->text, sNzeof(targetlink) \- 1);
l\->url = pdfioStringCreate(dd\->pdf, targetlink);
}
@ -2099,7 +2135,7 @@ Then it formats each cell using the format_block function described previously.
for (col = 0; col < num_cols; col ++)
{
dd|>y = row_y;
dd\->y = row_y;
format_block(dd, row\->cells[col], deffont, SIZE_TABLE, cols[col].left,
cols[col].right, /*leader*/NULL);

View File

@ -276,7 +276,8 @@ span.string {
</ul></li>
<li><a href="#examples">Examples</a><ul class="subcontents">
<li><a href="#read-pdf-metadata">Read PDF Metadata</a></li>
<li><a href="#create-pdf-file-with-text-and-image">Create PDF File With Text and Image</a></li>
<li><a href="#extract-text-from-pdf-file">Extract Text from PDF File</a></li>
<li><a href="#create-a-pdf-file-with-text-and-an-image">Create a PDF File With Text and an Image</a></li>
<li><a href="#generate-a-code-128-barcode">Generate a Code 128 Barcode</a></li>
<li><a href="#convert-markdown-to-pdf">Convert Markdown to PDF</a></li>
</ul></li>
@ -1197,7 +1198,39 @@ main(<span class="reserved">int</span> argc, <span clas
<span class="reserved">return</span> (<span class="number">0</span>);
}
</code></pre>
<h3 class="title" id="create-pdf-file-with-text-and-image">Create PDF File With Text and Image</h3>
<h3 class="title" id="extract-text-from-pdf-file">Extract Text from PDF File</h3>
<p>The <code>pdf2text.c</code> example code extracts non-Unicode text from a PDF file by scanning each page for strings and text drawing commands. Since it doesn't look at the font encoding or support Unicode text, it is really only useful to extract plain ASCII text from a PDF file. And since it writes text in the order it appears in the page stream, it may not come out in the same order as appears on the page.</p>
<p>The <a href="#pdfioStreamGetToken"><code>pdfioStreamGetToken</code></a> function is used to read individual tokens from the page streams. Tokens starting with the open parenthesis are text strings, while PDF operators are left as-is. We use some simple logic to make sure that we include spaces between text strings and add newlines for the text operators that start a new line in a text block:</p>
<pre><code class="language-c">pdfio_stream_t *st; <span class="comment">// Page stream</span>
<span class="reserved">bool</span> first = <span class="reserved">true</span>; <span class="comment">// First string on line?</span>
<span class="reserved">char</span> buffer[<span class="number">1024</span>]; <span class="comment">// Token buffer</span>
<span class="comment">// Read PDF tokens from the page stream...</span>
<span class="reserved">while</span> (pdfioStreamGetToken(st, buffer, <span class="reserved">sizeof</span>(buffer)))
{
<span class="reserved">if</span> (buffer[<span class="number">0</span>] == <span class="string">'('</span>)
{
<span class="comment">// Text string using an 8-bit encoding</span>
<span class="reserved">if</span> (first)
first = <span class="reserved">false</span>;
<span class="reserved">else</span> <span class="reserved">if</span> (buffer[<span class="number">1</span>] != <span class="string">' '</span>)
putchar(<span class="string">' '</span>);
fputs(buffer + <span class="number">1</span>, stdout);
}
<span class="reserved">else</span> <span class="reserved">if</span> (!strcmp(buffer, <span class="string">&quot;Td&quot;</span>) || !strcmp(buffer, <span class="string">&quot;TD&quot;</span>) || !strcmp(buffer, <span class="string">&quot;T*&quot;</span>) ||
!strcmp(buffer, <span class="string">&quot;\'&quot;</span>) || !strcmp(buffer, <span class="string">&quot;\&quot;&quot;</span>))
{
<span class="comment">// Text operators that advance to the next line in the block</span>
putchar(<span class="string">'\n'</span>);
first = <span class="reserved">true</span>;
}
}
<span class="reserved">if</span> (!first)
putchar(<span class="string">'\n'</span>);
</code></pre>
<h3 class="title" id="create-a-pdf-file-with-text-and-an-image">Create a PDF File With Text and an Image</h3>
<p>The <code>image2pdf.c</code> example code creates a PDF file containing a JPEG or PNG image file and optional caption on a single page. The <code>create_pdf_image_file</code> function creates the PDF file, embeds a base font and the named JPEG or PNG image file, and then creates a page with the image centered on the page with any text centered below:</p>
<pre><code class="language-c"><span class="directive">#include &lt;pdfio.h&gt;</span>
<span class="directive">#include &lt;pdfio-content.h&gt;</span>
@ -2000,7 +2033,7 @@ dd-&gt;y -= margin_top + lineheight;
<span class="reserved">char</span> targetlink[<span class="number">129</span>]; <span class="comment">// Targeted link</span>
targetlink[<span class="number">0</span>] = <span class="string">'#'</span>;
make_target_name(targetlink + <span class="number">1</span>, frag-&gt;text, <span class="reserved">sizeof</span>(targetlink) - <span class="number">1</span>);
make_target_name(targetlink + <span class="number">1</span>, frag-&gt;text, s¾zeof(targetlink) - <span class="number">1</span>);
l-&gt;url = pdfioStringCreate(dd-&gt;pdf, targetlink);
}
@ -2053,7 +2086,7 @@ dd-&gt;y -= margin_top + lineheight;
<span class="reserved">for</span> (col = <span class="number">0</span>; col &lt; num_cols; col ++)
{
ddì&gt;y = row_y;
dd-&gt;y = row_y;
format_block(dd, row-&gt;cells[col], deffont, SIZE_TABLE, cols[col].left,
cols[col].right, <span class="comment">/*leader*/</span>NULL);

View File

@ -922,8 +922,56 @@ main(int argc, // I - Number of command-line arguments
```
Create PDF File With Text and Image
-----------------------------------
Extract Text from PDF File
--------------------------
The `pdf2text.c` example code extracts non-Unicode text from a PDF file by
scanning each page for strings and text drawing commands. Since it doesn't
look at the font encoding or support Unicode text, it is really only useful to
extract plain ASCII text from a PDF file. And since it writes text in the order
it appears in the page stream, it may not come out in the same order as appears
on the page.
The [`pdfioStreamGetToken`](@@) function is used to read individual tokens from
the page streams. Tokens starting with the open parenthesis are text strings,
while PDF operators are left as-is. We use some simple logic to make sure that
we include spaces between text strings and add newlines for the text operators
that start a new line in a text block:
```c
pdfio_stream_t *st; // Page stream
bool first = true; // First string on line?
char buffer[1024]; // Token buffer
// Read PDF tokens from the page stream...
while (pdfioStreamGetToken(st, buffer, sizeof(buffer)))
{
if (buffer[0] == '(')
{
// Text string using an 8-bit encoding
if (first)
first = false;
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;
}
}
if (!first)
putchar('\n');
```
Create a PDF File With Text and an Image
----------------------------------------
The `image2pdf.c` example code creates a PDF file containing a JPEG or PNG
image file and optional caption on a single page. The `create_pdf_image_file`

View File

@ -23,6 +23,7 @@ TARGETS = \
code128 \
image2pdf \
md2pdf \
pdf2text \
pdfioinfo
@ -50,6 +51,11 @@ 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)

View File

@ -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;
}

View File

@ -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>

View File

@ -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>