Add additional interface for filtering page contents

6 files changed, 170 insertions, 3 deletions

diff --git a/examples/build.mk b/examples/build.mk
index f5b44669..b5748c11 100644
--- a/examples/build.mk
+++ b/examples/build.mk
@@ -7,7 +7,8 @@ BINS_examples = \
 	pdf-create \
 	pdf-parse-content \
 	pdf-split-pages \
-	pdf-filter-tokens
+	pdf-filter-tokens \
+	pdf-count-strings
 CBINS_examples = pdf-linearize
 
 TARGETS_examples = $(foreach B,$(BINS_examples) $(CBINS_examples),examples/$(OUTPUT_DIR)/$(call binname,$(B)))
diff --git a/examples/pdf-count-strings.cc b/examples/pdf-count-strings.cc
new file mode 100644
index 00000000..81718298
--- /dev/null
+++ b/examples/pdf-count-strings.cc
@@ -0,0 +1,131 @@
+//
+// This example illustrates the use of QPDFObjectHandle::TokenFilter
+// with filterPageContents. See also pdf-filter-tokens.cc for an
+// example that uses QPDFObjectHandle::TokenFilter with
+// addContentTokenFilter.
+//
+
+#include <iostream>
+#include <string.h>
+#include <stdlib.h>
+
+#include <qpdf/QPDF.hh>
+#include <qpdf/QUtil.hh>
+#include <qpdf/QPDFObjectHandle.hh>
+#include <qpdf/Pl_StdioFile.hh>
+
+static char const* whoami = 0;
+
+void usage()
+{
+    std::cerr << "Usage: " << whoami << " infile" << std::endl
+	      << "Applies token filters to infile"
+              << std::endl;
+    exit(2);
+}
+
+class StringCounter: public QPDFObjectHandle::TokenFilter
+{
+  public:
+    StringCounter() :
+        count(0)
+    {
+    }
+    virtual ~StringCounter()
+    {
+    }
+    virtual void handleToken(QPDFTokenizer::Token const&);
+    virtual void handleEOF();
+    int getCount() const;
+
+  private:
+    int count;
+};
+
+void
+StringCounter::handleToken(QPDFTokenizer::Token const& token)
+{
+    // Count string tokens
+    if (token.getType() == QPDFTokenizer::tt_string)
+    {
+        ++this->count;
+    }
+    // Preserve input verbatim by passing each token to any specified
+    // downstream filter.
+    writeToken(token);
+}
+
+void
+StringCounter::handleEOF()
+{
+    // Write a comment at the end of the stream just to show how we
+    // can enhance the output if we want.
+    write("\n% strings found: ");
+    write(QUtil::int_to_string(this->count));
+    // If you override handleEOF, you must always remember to call finish().
+    finish();
+}
+
+int
+StringCounter::getCount() const
+{
+    return this->count;
+}
+
+int main(int argc, char* argv[])
+{
+    whoami = QUtil::getWhoami(argv[0]);
+
+    // For libtool's sake....
+    if (strncmp(whoami, "lt-", 3) == 0)
+    {
+	whoami += 3;
+    }
+
+    if (argc != 2)
+    {
+	usage();
+    }
+    char const* infilename = argv[1];
+
+    try
+    {
+	QPDF pdf;
+	pdf.processFile(infilename);
+        std::vector<QPDFObjectHandle> pages = pdf.getAllPages();
+        int pageno = 0;
+        for (std::vector<QPDFObjectHandle>::iterator iter = pages.begin();
+             iter != pages.end(); ++iter)
+        {
+            QPDFObjectHandle page = *iter;
+            ++pageno;
+            // Pass the contents of a page through our string counter.
+            // If it's an even page, capture the output. This
+            // illustrates that you may capture any output generated
+            // by the filter, or you may ignore it.
+            StringCounter counter;
+            if (pageno % 2)
+            {
+                // Ignore output for odd pages.
+                page.filterPageContents(&counter);
+            }
+            else
+            {
+                // Write output to stdout for even pages.
+                Pl_StdioFile out("stdout", stdout);
+                std::cout << "% Contents of page " << pageno << std::endl;
+                page.filterPageContents(&counter, &out);
+                std::cout << "\n% end " << pageno << std::endl;
+            }
+            std::cout << "Page " << pageno
+                      << ": strings = " << counter.getCount() << std::endl;
+        }
+    }
+    catch (std::exception& e)
+    {
+	std::cerr << whoami << ": " << e.what() << std::endl;
+	exit(2);
+    }
+
+    return 0;
+}
diff --git a/examples/pdf-filter-tokens.cc b/examples/pdf-filter-tokens.cc
index 2566f72c..809c160b 100644
--- a/examples/pdf-filter-tokens.cc
+++ b/examples/pdf-filter-tokens.cc
@@ -1,6 +1,8 @@
 //
-// This example illustrates the use of QPDFObjectHandle::TokenFilter.
-// Please see comments inline for details.
+// This example illustrates the use of QPDFObjectHandle::TokenFilter
+// with addContentTokenFilter. Please see comments inline for details.
+// See also pdf-count-strings.cc for a use of
+// QPDFObjectHandle::TokenFilter with filterPageContents.
 //
 
 #include <iostream>
diff --git a/examples/qtest/count-strings.test b/examples/qtest/count-strings.test
new file mode 100644
index 00000000..ba3f835b
--- /dev/null
+++ b/examples/qtest/count-strings.test
@@ -0,0 +1,17 @@
+#!/usr/bin/env perl
+require 5.008;
+BEGIN { $^W = 1; }
+use strict;
+
+chdir("count-strings");
+
+require TestDriver;
+
+my $td = new TestDriver('pdf-count-strings');
+
+$td->runtest("filter tokens",
+	     {$td->COMMAND => "pdf-count-strings in.pdf"},
+	     {$td->FILE => "out", $td->EXIT_STATUS => 0},
+             $td->NORMALIZE_NEWLINES);
+
+$td->report(1);
diff --git a/examples/qtest/count-strings/in.pdf b/examples/qtest/count-strings/in.pdf
new file mode 100644
index 00000000..591614c4
--- /dev/null
+++ b/examples/qtest/count-strings/in.pdf
diff --git a/examples/qtest/count-strings/out b/examples/qtest/count-strings/out
new file mode 100644
index 00000000..87b024fc
--- /dev/null
+++ b/examples/qtest/count-strings/out
@@ -0,0 +1,16 @@
+Page 1: strings = 3
+% Contents of page 2
+BT
+  /F1 24 Tf
+  72 720 Td
+  (Four ) Tj
+  (Five ) Tj
+  (Six )
+  (beautiful ) Tj
+  (strings) Tj
+  (!) Tj
+ET
+
+% strings found: 6
+% end 2
+Page 2: strings = 6